paper.md

• NeRFPlayer
• D-NeRF
• Zip-NeRF
• LERF
• LERF-TOGO
• GARField
• LangSplat
• Tensor4D
• DepthSplat: Connecting Gaussian Splatting and Depth
• DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
• MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes
• L3DG: Latent 3D Gaussian Diffusion
• Differentiable Robot Rendering
• Object Pose Estimation Using Implicit Representation For Transparent Objects
• Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices
• Diffusion Models in 3D Vision: A Survey
• Magnituder Layers for Implicit Neural Representations in 3D
• NeRF-enabled Analysis-Through-Synthesis for ISAR Imaging of Small Everyday Objects with Sparse and Noisy UWB Radar Data
• EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse View
• 4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting
• 4-LEGS: 4D Language Embedded Gaussian Splatting
• Scalable Indoor Novel-View Synthesis using Drone-Captured 360 Imagery with 3D Gaussian Splatting
• Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting
• GSORB-SLAM: Gaussian Splatting SLAM benefits from ORB features and Transmittance information
• LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images
• SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection
• Gaussian Splatting Visual MPC for Granular Media Manipulation
• GS^3: Efficient Relighting with Triple Gaussian Splatting
• 3D Gaussian Splatting in Robotics: A Survey
• FreeNeRF
• InstantSplat
• EmerNeRF
• DistillNeRF
• JacobiNeRF
• Efficient Geometry-aware 3D Generative Adversarial Networks
• MultiPhys: Multi-Person Physics-aware 3D Motion Estimation
• ActAnywhere
• Instruct-NeRF2NeRF
• GenN2N
• LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
• Sort-free Gaussian Splatting via Weighted Sum Rendering
• VR-Splatting: Foveated Radiance Field Rendering via 3D Gaussian Splatting and Neural Points
• EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting
• 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
• PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
• 3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
• Fully Explicit Dynamic Gaussian Splatting
• SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes
• Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling
• E-3DGS: Gaussian Splatting with Exposure and Motion Events
• AG-SLAM: Active Gaussian Splatting SLAM
• 3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
• Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
• Real-time 3D-aware Portrait Video Relighting
• Few-shot NeRF by Adaptive Rendering Loss Regularization
• FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors
• Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
• SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering
• NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance
• MuRF: Multi-Baseline Radiance Fields
• NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis
• Mip-Splatting: Alias-free 3D Gaussian Splatting
• Factor Fields: A Unified Framework for Neural Fields and Beyond
• LaRa: Efficient Large-Baseline Radiance Fields
• GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyond
• NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance
• GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
• 3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting
• Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
• High-quality Surface Reconstruction using Gaussian Surfels
• PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
• Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering
• Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting
• SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing
• LargeSpatialModel: End-to-end Unposed Images to Semantic 3D
• RaDe-GS: Rasterizing Depth in Gaussian Splatting
• GaussianPro: 3D Gaussian Splatting with Progressive Propagation
• Trim 3D Gaussian Splatting for Accurate Geometry Representation
• PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
• Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration
• GS-ID: Illumination Decomposition on Gaussian Splatting via Diffusion Prior and Parametric Light Source Optimization
• GS-IR: 3D Gaussian Splatting for Inverse Rendering
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
• Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
• MVSNeRF
• GeoNeRF
• Slowfast networks for video recognition
• A closer look at spatiotemporal convolutions for action recognition
• Sementic Gaussians
• A Survey on 3D Gaussian Splatting
• Photo Tourism: Exploring Photo Collections in 3D
• Multi-View Stereo for Community Photo Collections
• Light Field Rendering.pdf
• The Lumigraph
• Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
• Deep blending for free-viewpoint image-based rendering
• Deferred neural rendering: Image synthesis using neural textures
• DeepVoxels: Learning Persistent 3D Feature Embeddings
• Neural Point-Based Graphics
• ADOP: Approximate Differentiable One-Pixel Point Rendering
• GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering
• FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
• GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
• Scaffold-gs: Structured 3d gaussians for view-adaptive rendering
• Geogaussian: Geometry-aware gaussian splatting for scene rendering
• Gaussianpro: 3d gaussian splatting with progressive propagation
• COLMAP-Free 3D Gaussian Splatting
• Fsgs: Real-time fewshot view synthesis using gaussian splatting
• DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
• MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
• Corgs: Sparse-view 3d gaussian splatting via co-regularization
• pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
• Splatter image: Ultra-fast single-view 3d reconstruction
• Compact 3d gaussian representation for radiance field
• Hac: Hash-grid assisted context for 3d gaussian splatting compression
• Reducing the memory footprint of 3d gaussian splatting
• Compressed 3d gaussian splatting for accelerated novel view synthesis
• Gaussianshader: 3d gaussian splatting with shading functions for reflective surfaces
• Relightable gaussian codec avatars
• Mirror-3dgs: Incorporating mirror reflections into 3d gaussian splatting
• Scaffold-gs: Structured 3d gaussians for view-adaptive rendering
• GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal
• Language embedded 3d gaussians for open-vocabulary scene understanding
• Feature 3dgs: Supercharging 3d gaussian splatting to enable distilled feature fields
• mgs: Foundation model embedded 3d gaussian splatting for holistic 3d scene understanding,
• Gaussian grouping: Segment and edit anything in 3d scenes
• Segment any 3d gaussians
• Gaussian-flow: 4d reconstruction with dynamic 3d gaussian particle
• Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
• Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
• Gaussian Splatting in Stylefde
• DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark
• TOGS: Gaussian Splatting with Temporal Opacity Offset for Real-Time 4D DSA Rendering
• Dual-Camera Smooth Zoom on Mobile Phones
• Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
• CoGS: Controllable Gaussian Splatting
• GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time
• Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
• Neural parametric gaussians for monocular non-rigid object reconstruction
• Control4d: Efficient 4d portrait editing with text
• Dynmf: Neural motion factorization for real-time dynamic view synthesis with 3d gaussian splatting
• Swags: Sampling windows adaptively for dynamic 3d gaussian splatting
• Gaufre: Gaussian deformation fields for real-time dynamic novel view synthesis
• An efficient 3d gaussian representation for monocular/multi-view dynamic scenes
• Motion-aware 3d gaussian splatting for efficient dynamic scene reconstruction
• 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis
• DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes
• Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
• HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
• A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets
• CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians
• VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
• Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
• On Scaling Up 3D Gaussian Splatting Training
• HGS-Mapping: Online Dense Mapping Using Hybrid Gaussian Representation in Urban Scenes
• GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting
• MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
• SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
• Gaussian Splatting SLAM
• Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
• High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization
• Image Quality Assessment: From Error Visibility to Structural Similarity
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
• HexPlane: A Fast Representation for Dynamic Scenes
• Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction
• Forward Flow for Novel View Synthesis of Dynamic Scenes
• VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality
• Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
• Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians
• MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
• GaussReg: Fast 3D Registration with Gaussian Splatting
• GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
• Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering
• AutoInt: Automatic Integration for Fast Neural Volume Rendering
• Neural Sparse Voxel Fields
• Learned Initializations for Optimizing Coordinate-Based Neural Representations
• DeRF: Decomposed Radiance Fields
• Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
• Space-time Neural Irradiance Fields for Free-Viewpoint Video
• Neural Radiance Flow for 4D View Synthesis and Video Processing
• STaR: Bootstrapping Reasoning With Reasoning
• Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video
• Portrait Neural Radiance Fields from a Single Image
• NeRV: Neural Representations for Videos
• NeRD: Neural Reflectance Decomposition from Image Collections
• Neural Reflectance Fields for Appearance Acquisition
• pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
• Object-Centric Neural Scene Rendering
• GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
• Neural Scene Graphs for Dynamic Scenes
• INeRF: Inverting Neural Radiance Fields for Pose Estimation
• Dense Depth Priors for Neural Radiance Fields from Sparse Input Views
• MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis
• Single-View View Synthesis with Multiplane Images
• FWD: Real-time Novel View Synthesis with Forward Warping and Depth
• Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation
• RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
• GRF: Learning a General Radiance Field for 3D Representation and Rendering
• IBRNet: Learning Multi-View Image-Based Rendering
• Depth-supervised NeRF: Fewer Views and Faster Training for Free
• Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes
• Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
• NeROIC: Neural Rendering of Objects from Online Image Collections
• Neural Scene Graphs for Dynamic Scenes
• CG-NeRF: Conditional Generative Neural Radiance Fields
• Neural 3D Video Synthesis from Multi-view Video
• TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
• Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video
• HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
• Neural Radiance Flow for 4D View Synthesis and Video Processing
• Weakly Supervised 3D Open-vocabulary Segmentation
• ScanQA: 3D Question Answering for Spatial Scene Understanding
• IQA: Visual Question Answering in Interactive Environments
• SimVQA: Exploring Simulated Environments for Visual Question Answering
• Visual Language Maps for Robot Navigation
• Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
• In-Place Scene Labelling and Understanding with Implicit Scene Representation
• Decomposing NeRF for Editing via Feature Field Distillation
• ConceptFusion: Open-set Multimodal 3D Mapping
• Weakly Supervised 3D Open-vocabulary Segmentation
• Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations
• Language-driven Semantic Segmentation
• Emerging Properties in Self-Supervised Vision Transformers
• In-Place Scene Labelling and Understanding with Implicit Scene Representation
• Panoptic Lifting for 3D Scene Understanding with Neural Fields
• OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression
• Learning Transferable Visual Models From Natural Language Supervision
• CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory
• Learning to Prompt for Vision-Language Models
• Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness
• Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
• MVSNet: Depth Inference for Unstructured Multi-view Stereo
• A theory of shape by space carving
• Shape and Motion from Image Streams under Orthography: A Factorization Method

<<<<<<< HEAD

• Structure-from-Motion Revisited

• InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering

• pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

• The Platonic Representation Hypothesis

• A Survey on Multimodal Large Language Models

• DINOv2: Learning Robust Visual Features without Supervision

• SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

• Improving 2D Feature Representations by 3D-Aware Fine-Tuning

• OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding

• ICARUS: A Specialized Architecture for Neural Radiance Fields Rendering

• Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction

• Anisotropic Fourier Features for Neural Image-Based Rendering and Relighting

• GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

• Improving 2D Feature Representations by 3D-Aware Fine-Tuning

• Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

• OpenMask3D: Open-Vocabulary 3D Instance Segmentation

• OPENNERF: OPEN SET 3D NEURAL SCENE SEGMEN- TATION WITH PIXEL-WISE FEATURES AND RENDERED NOVEL VIEWS

• SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes

• Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds

• Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

• AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

• 3D Segmentation of Humans in Point Clouds with Synthetic Data

• Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

• Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes

• Mix3D: Out-of-Context Data Augmentation for 3D Scenes

• 4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation

• GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

• Splatter a Video: Video Gaussian Representation for Versatile Processing

• CONTINUOUS AND DISCRETE WAVELET TRANSFORMS

• Discrete Cosine Transfonn

• Implicit Neural Representations with Periodic Activation Functions

• Compositional pattern producing networks: A novel abstraction of development

• COIN++: Neural Compression Across Modalities

• COIN: COmpression with Implicit Neural representations

• Compression with Bayesian Implicit Neural Representations

• Implicit Neural Representations for Image Compression

• Single Image Defocus Deblurring via Implicit Neural Inverse Kernels

• Signal Processing for Implicit Neural Representations

• Revisiting Implicit Neural Representations in Low-Level Vision

• Learning Continuous Image Representation with Local Implicit Image Function

• Single Image Super-Resolution via a Dual Interactive Implicit Neural Network

• Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs

• WIRE: Wavelet Implicit Neural Representations

• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

• NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions

• ACORN: Adaptive Coordinate Networks for Neural Scene Representation

• Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

• LSQ+: Improving low-bit quantization through learnable offsets and better initialization

• SoundStream: An End-to-End Neural Audio Codec

• Split Hierarchical Variational Compression

• Practical Lossless Compression with Latent Variables using Bits Back Coding

• Point-NeRF: Point-based Neural Radiance Fields

• HNeRV: A Hybrid Neural Representation for Videos

• NeRV: Neural Representations for Videos

• E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context

• Boosting Neural Representations for Videos with a Conditional Decoder

• Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis

• 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

• Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

• GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

• Text-to-3D using Gaussian Splatting

• Drivable 3D Gaussian Avatars

• Density Modeling of Images using a Generalized Normalization Transformation

• Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules

• ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

• Learned Image Compression with Mixed Transformer-CNN Architectures

• End-to-end Optimized Image Compression

• Variational image compression with a scale hyperprior

• Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression

• Joint Autoregressive and Hierarchical Priors for Learned Image Compression

• COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec

• Low-complexity Overfitted Neural Image Codec

• Split Hierarchical Variational Compression

• Practical Lossless Compression with Latent Variables using Bits Back Coding

• SoundStream: An End-to-End Neural Audio Codec

• Practical Lossless Compression with Latent Variables using Bits Back Coding

• Entropy Coding of Unordered Data Structures

• Occupancy Networks: Learning 3D Reconstruction in Function Space

• Boosting Neural Representations for Videos with a Conditional Decoder

• 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos

• 4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes

• EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction

• NERV++: An Enhanced Implicit Neural Video Representation

• T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

• VideoLCM: Video Latent Consistency Model

• Generating 3D-Consistent Videos from Unposed Internet Photos

• ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation

• Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases

• MixConv: Mixed Depthwise Convolutional Kernels

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

• Handbook of image and video processing

• Layered neural atlases for consistent video editing.

• Consistent video depth estimation.

• Representing moving images with layers

• Deformable sprites for unsupervised video decomposition

• Space-time correspondence as a contrastive random walk.

• Codef: Content deformation fields for temporally consistent video processing.

• Gendef: Learning generative deformation field for video generation.

• Mft: Long-term tracking of every pixel

• Layered neural rendering for retiming people in video.

• Inve: Interactive neural video editing.

• Tracking everything everywhere all at once

• Raft: Recurrent all-pairs field transforms for optical flow

• Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

• Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

• Diffusion models trained with large data are transferable visual models

• Layered Neural Atlases for Consistent Video Editing

• GenDeF: Learning Generative Deformation Field for Video Generation

• CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

• Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time

• MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

• VidToMe: Video Token Merging for Zero-Shot Video Editing

• Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories

• CoTracker: It is Better to Track Together

• TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

• MFT: Long-Term Tracking of Every Pixel

• Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis

• SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

• 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos

• Neural trajectory fields for dynamic novel view synthesis.

• Dynibar: Neural dynamic image-based rendering.

• Dynmf: Neural motion factorization for real-time dynamic view synthesis with 3d gaussian splatting.

• Gaussian-flow: 4d reconstruction with dynamic 3d gaussian particle.

• Trajectory space: A dual representation for nonrigid structure from motion.

• q-bernstein polynomials and bézier curves.

• B-spline curves and surfaces.

• Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

• Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

• Density estimation using Real NVP.

• Shape of Motion: 4D Reconstruction from a Single Video

• 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

• Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting

• 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors

• 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting

• Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

• Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators

• Make-A-Video: Text-to-Video Generation without Text-Video Data

• LetsTalk: Latent Diffusion Transformer for Talking Video Synthesis

• Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction

• DiffGS: Functional Gaussian Splatting Diffusion

• HexPlane: A Fast Representation for Dynamic Scenes

• Suds: Scalable urban dynamic scenes

• Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis

• BANMo: Building Animatable 3D Neural Models from Many Casual Videos

• Humanrf: High-fidelity neural radiance fields for humans in motion.

• Tava: Template-free animatable volumetric actors.

• High-Resolution Image Synthesis with Latent Diffusion Models

• Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

• PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

• Scalable Diffusion Models with Transformers

• All are Worth Words: A ViT Backbone for Diffusion Models

• Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting

• Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections

• Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

• Denoising diffusion probabilistic models.

• Taming Transformers for High-Resolution Image Synthesis

• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

• A Survey on Video Diffusion Models

• Diffusion Models and Representation Learning: A Survey

• Diffusion Models: A Comprehensive Survey of Methods and Applications

• From Sora What We Can See: A Survey of Text-to-Video Generation

• VDT: General-purpose Video Diffusion Transformers via Mask Modeling

• Latte: Latent Diffusion Transformer for Video Generation

• Scalable Diffusion Models with Transformers

• VideoCrafter1: Open Diffusion Models for High-Quality Video Generation

• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

• VideoComposer: Compositional Video Synthesis with Motion Controllability

• Imagen Video: High Definition Video Generation with Diffusion Models

• Diffusion Models Beat GANs on Image Synthesis

• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

• Video Diffusion Models

• Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

• Neural Network Parameter Diffusion

• WonderWorld: Interactive 3D Scene Generation from a Single Image

• Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videos

• Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

• Adding Conditional Control to Text-to-Image Diffusion Models

• IC-light

• Tutorial on Variational Autoencoders

• Quadratic Gaussian Splatting for Efficient and Detailed Surface Reconstruction

• HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

• VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

• SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

• DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

• DUSt3R: Geometric 3D Vision Made Easy

• MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification

• Stopthepop: Sorted gaussian splatting for view-consistent real-time rendering.

• Rade-gs: Rasterizing depth in gaussian splatting.

• Pgsr: Planar-based gaussian splatting for efficient and high-fidelity surface reconstruction.

• MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

• The Scene Language: Representing Scenes with Programs, Words, and Embeddings

• Autoregressive Image Generation without Vector Quantization

• PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence

• SAMPart3D: Segment Any Part in 3D Objects

• LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

• EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

• GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling

• CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

• Image Neural Field Diffusion Models

• Neural Gaussian Scale-Space Fields

• NICE: Non-linear Independent Components Estimation

• AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models

• Scalable diffusion models with transformers

• Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

• Motion Prompting: Controlling Video Generation with Motion Trajectories

• A Survey on Video Diffusion Models

• Video Diffusion Models

• Make-A-Video: Text-to-Video Generation without Text-Video Data

• Imagen Video: High Definition Video Generation with Diffusion Models

• Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

• Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation

• Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation

• LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models

• Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation

• SimDA: Simple Diffusion Adapter for Efficient Video Generation

• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

• VideoCrafter1: Open Diffusion Models for High-Quality Video Generation

• VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

• Make Pixels Dance: High-Dynamic Video Generation

• Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

• MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

• LaMD: Latent Motion Diffusion for Video Generation

• Video Probabilistic Diffusion Models in Projected Latent Space

• Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

• VDT: General-purpose Video Diffusion Transformers via Mask Modeling

• Latte: Latent Diffusion Transformer for Video Generation

• Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs

• TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

• Generative Image Dynamics

• Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

• Motion Prompting: Controlling Video Generation with Motion Trajectories

• SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

• REDUCIO! Generating 1024×1024 Video within 16 Seconds using Extremely Compressed Motion Latents

• DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

• InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

• Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

• Pixart-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis.

• Learning Continuous Image Representation with Local Implicit Image Function

• FeatUp: A Model-Agnostic Framework for Features at Any Resolution

• Ref-GS: Directional Factorization for 2D Gaussian Splatting

• GS-ID: Illumination Decomposition on Gaussian Splatting via Diffusion Prior and Parametric Light Source Optimization

• 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

• Feat2GS: Probing Visual Foundation Models with Gaussian Splatting

• MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field

• Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps

• Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

• LRM: Large Reconstruction Model for Single Image to 3D

• CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner

• 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models

• CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

• You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

• Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model

• Evaluating Multiview Object Consistency in Humans and Image Models

• MeshArt: Generating Articulated Meshes with Structure-guided Transformers

• Flow Matching for Generative Modeling

• Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields

• Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale

• Structured 3D Latents for Scalable and Versatile 3D Generation

• LEARNING INTERACTIVE REAL-WORLD SIMULATORS