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
PrEditor3D: Fast and Precise 3D Shape Editing
Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing
Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation
Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models
Prior-free 3D Object Tracking
ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
Probabilistic Prompt Distribution Learning for Animal Pose Estimation
Probability Density Geodesics in Image Diffusion Latent Space
ProbeSDF: Light Field Probes For Neural Surface Reconstruction
Probing the Mid-level Vision Capabilities of Self-Supervised Learning
ProbPose: A Probabilistic Approach to 2D Human Pose Estimation
Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions
Progress-Aware Video Frame Captioning
Progressive Correspondence Regenerator for Robust 3D Registration
Progressive Focused Transformer for Single Image Super-Resolution
Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data
ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector
Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models
Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation
Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attack on Breast Ultrasound Images
Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
PromptHash: Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval
PromptHMR: Promptable Human Mesh Recovery
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
ProReflow: Progressive Reflow with Decomposed Velocity
Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing
Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation
Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging
ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding
PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention
PS-EIP: Robust Photometric Stereo Based on Event Interval Profile
Pseudo Visible Feature Fine-Grained Fusion for Thermal Object Detection
PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model
PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting
PURA: Parameter Update-Recovery Test-Time Adaption for RGB-T Tracking
Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction
Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs
Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content

« prev Page 41/59 next »