CVPR 2025

2,907 papers

Top Research Directions

Research directions most represented by CVPR 2025 papers.

Overcoming the Static Scene Assumption 49
Mitigating Multi View Inconsistency in Generative 3D Modeling 48
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 42
Generalizing from Synthetic Data to the Real World 39
Material Lighting Disentanglement for 3D Reconstruction 37
Spatial Attention Masking in Generative Diffusion Models 36
Error Propagation in Monocular Depth Priors 32
Overcoming the Iterative Inference Latency of Diffusion Models 31
Exploiting Temporal Redundancy in Video Neural Networks 29
Aligning Global Semantics with Local Spatial Precision 28
Scaling Visual Attention Beyond Quadratic Complexity 28
Accelerating Neural Scene Representations for Real Time Rendering 27
Visual Grounding and Hallucination in Vision Language Models 27
Completing Unobserved Geometry with Generative Diffusion Priors 24
The Cross Modal Representation Gap 24

Top Authors

AuthorPapers
Yujun Shen17
Marc Pollefeys15
Daniel Cremers13
Jian Yang13
Jan Kautz11
Ziwei Liu11
Federico Tombari10
Guangtao Zhai10
Jiangning Zhang10
Christian Theobalt9
Jiajun Wu9
Ming-Hsuan Yang9
Ranjay Krishna9
Wei-Shi Zheng9
Xiongkuo Min9
Zhe Lin9
Zheng-Jun Zha9
Andrea Vedaldi8
Chen Change Loy8
Cheng Wang8

Impactful Papers

Papers from CVPR 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration
Using Diffusion Priors for Video Amodal Segmentation
Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing
USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping
UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing
V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts
V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection
Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models
VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis
v-CLR: View-Consistent Learning for Open-World Instance Segmentation
VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment
VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness
vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation
VEU-Bench: Towards Comprehensive Understanding of Video Editing
VGGT: Visual Geometry Grounded Transformer
VI^3NR: Variance Informed Initialization for Implicit Neural Representations
ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation
Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior
Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation
Video-Bench: Human-Aligned Video Generation Benchmark
Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Video Depth without Video Models
VideoDirector: Precise Video Editing via Text-to-Video Models
VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
VideoGEM: Training-free Action Grounding in Videos
VideoGigaGAN: Towards Detail-rich Video Super-Resolution
VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
Video-Guided Foley Sound Generation with Multimodal Controls
VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
Video Language Model Pretraining with Spatio-temporal Masking
VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Video Motion Transfer with Diffusion Transformers
Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing
Video Summarization with Large Language Models

« prev Page 56/59 next »