• OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels, CVPR 2025. [Paper | Code]

• Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space, CVPR 2025. [Paper | Project | Code]

• 3D Student Splatting and Scooping, CVPR 2025. [Paper | Code]

• CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models, CVPR 2025. [Paper | Project | Code]

• Reconstructing Humans with a Biomechanically Accurate Skeleton, CVPR 2025. [Paper | Project | Code]

• Multi-view Reconstruction via SfM-guided Monocular Depth Estimation, CVPR 2025. [Paper | Project | Code]

• Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models, CVPR 2025. [Paper | Project | Code]

• CustAny: Customizing Anything from A Single Example, CVPR 2025. [Paper | Project | Code]

• VGGT: Visual Geometry Grounded Transformer, CVPR 2025. [Paper | Project | Code] 🏆🏆🏆

• Navigation World Models, CVPR 2025. [Paper | Project | Code]

• MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos, CVPR 2025. [Paper | Project | Code]

• Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos, CVPR 2025. [Paper | Project | Code]

• FoundationStereo: Zero-Shot Stereo Matching, CVPR 2025. [Paper | Project | Code]

• Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models, CVPR 2025. [Paper | Code]

• The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition, CVPR 2025. [Paper | Project]

• Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis, CVPR 2025. [Paper | Project | Code]

• Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing, CVPR 2025. [Paper | Project | Code]

• MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds, CVPR 2025. [Paper | Project | Code]

• TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization, CVPR 2025. [Paper | Project | Code]

• Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models, CVPR 2025. [Paper | Code]

• Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models, CVPR 2025. [Paper | Project | Code]

• DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models, CVPR 2025. [Paper | Project | Code] ]

• FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video, CVPR 2025. [Paper | Project | Code]

• OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation, CVPR 2025. [Paper | Project | Code]

• RandAR: Decoder-only Autoregressive Visual Generation in Random Orders, CVPR 2025. [Paper | Project | Code]

• Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing, CVPR 2025. [Paper | Project | Code]

• AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea, CVPR 2025. [Paper | Project | Code]

• VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection, CVPR 2025. [Paper | Code]

• SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing, CVPR 2025. [Paper | Project | Code]

• OPA-DPO: Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key, CVPR 2025. [Paper | Project | Code]

• Minority-Focused Text-to-Image Generation via Prompt Optimization, CVPR 2025. [Paper | Code]

• Autoregressive Distillation of Diffusion Transformers, CVPR 2025. [Paper | Code]

• Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks, CVPR 2025. [Paper | Code]

• TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion, CVPR 2025. [Paper | Code]

• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models, CVPR 2025. [Paper | Blog | Code]

• CUT3R: Continuous 3D Perception Model with Continuous 3D Perception Model with Persistent State State, CVPR 2025. [Paper | Project | Code]

• Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key, CVPR 2025. [Paper | Project | Code]

• Birth and Death of a Rose, CVPR 2025. [Paper | Project | Code]

• Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content, CVPR 2025. [Paper | Code]

• Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector, CVPR 2025. [Paper | Code]

• Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation, CVPR 2025. [Paper | Code]

• LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models, CVPR 2025. [Paper]

• FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity, CVPR 2025. [Paper]

• Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces, CVPR 2025. [Paper | Project | Code]

• Video-XL Family: Efficient VLMs for Extremely Long Video Understanding, CVPR 2025. [Paper| Code]

• Neural Inverse Rendering from Propagating Light, CVPR 2025. [Paper | Project | Code] 🏆🏆🏆

• MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision, CVPR 2025. [Paper | Project | Code]

• Motion Prompting: Controlling Video Generation with Motion Trajectories, CVPR 2025. [Paper | Project]

• Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise, CVPR 2025. [Paper | Project | Code]

• LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping, CVPR 2025. [Paper | Project]

• LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions, CVPR 2025. [Paper | Code]

• Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild, CVPR 2025. [Paper | Project]

• CleanDIFT: Diffusion Features without Noise, CVPR 2025. [Paper | Project | Code]

• Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather, CVPR 2025. [Paper]

• DiffFNO: Diffusion Fourier Neural Operator, CVPR 2025. [Paper | Project]

• Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining, CVPR 2025. [Paper]

• CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner, CVPR 2025. [Paper | Project | Code]

• Reanimating Images using Neural Representations of Dynamic Stimuli, CVPR 2025. [Paper]

• EgoLM: Multi-Modal Language Model of Egocentric Motions, CVPR 2025. [Paper | Project]

• MEGA: Masked Generative Autoencoder for Human Mesh Recovery, CVPR 2025. [Paper]

• Descriptor-In-Pixel : Point-Feature Tracking for Pixel Processor Arraysr, CVPR 2025. [Project]

• Temporally Consistent Object-Centric Learning by Contrasting Slots, CVPR 2025. [Paper | Project | Code]

• Temporal Alignment-Free Video Matching for Few-shot Action Recognition, CVPR 2025. [Paper | Project | Code]

• One Category One Prompt: Dataset Distillation using Diffusion Models, CVPR 2025. [Paper | Code]

• IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior, CVPR 2025. [Paper]

• Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning, CVPR 2025. [Paper]

• Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation, CVPR 2025. [Paper]

• Identifying and Mitigating Position Bias of Multi-image Vision-Language Models, CVPR 2025. [Paper]

• From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons, CVPR 2025. [Paper]

• Language-Guided Image Tokenization for Generation, CVPR 2025. [Paper | Project]

• DreamRelation: Bridging Customization and Relation Generation, CVPR 2025. [Paper | Project | Code]

• GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skills, CVPR 2025. [Paper | Project | Code]

• Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning, CVPR 2025. [Project]

• DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution, CVPR 2025. [Paper |Code]

• Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World, CVPR 2025. [Paper|Code]

• Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues, CVPR 2025.[Project]

• Camera resection from known line pencils and a radially distorted scanline, CVPR 2025. [Code]

• Opportunistic Single-Photon Time of Flight, CVPR 2025. [Paper]

• DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models, CVPR 2025. [Paper]

• DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution, CVPR 2025. [Paper | Code]

• UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming, CVPR 2025. [Paper]

• Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning, CVPR 2025. [Paper | Code]

• Enhancing Diversity for Data-free Quantization, CVPR 2025. [Paper]

• TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model, CVPR 2025. [Paper | Code]

• Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation, CVPR 2025. [Paper]

• Time of the Flight of the Gaussians: Fast and Accurate Dynamic Time-of-Flight Radiance Field, CVPR 2025. [Paper | Project | Code]

• Zero-Shot Monocular Scene Flow Estimation in the Wild, CVPR 2025. [Paper | Project]

• DNF: Unconditional 4D Generation with Dictionary-based Neural Fields, CVPR 2025. [Paper | Project | Code]

• CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models, CVPR 2025. [Paper | Project]

• Effective SAM Combination for Open-Vocabulary Semantic Segmentation, CVPR 2025. [Paper]

• Removing Reflections from RAW Photos, CVPR 2025. [Paper | Project]

• Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens, CVPR 2025. [Paper | Project | Code]

• Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding, CVPR 2025. [Paper | Project | Code]

• Towards Vision Language Models For Extra-Long Video Understanding, CVPR 2025. [Paper | Code]

• SEAL: Semantic Attention Learning for Long Video Representation, CVPR 2025. [Paper]

• Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval, CVPR 2025. [Paper]

We would like to express our gratitude for the code repository provided in cvpr25_oral_gpu_info.