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
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport
Recovering Dynamic 3D Sketches from Videos
Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification
Rectified Diffusion Guidance for Conditional Generation
Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
Redefining in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection
Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
Reference-Based 3D-Aware Image Editing with Triplanes
Ref-GS: Directional Factorization for 2D Gaussian Splatting
RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects
Region-Based Representations Revisited
Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model
Relation3D : Enhancing Relation Modeling for Point Cloud Instance Segmentation
RelationField: Relate Anything in Radiance Fields
Relation-Rich Visual Document Generator for Visual Information Extraction
Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization
RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations
Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios
Removing Reflections from RAW Photos
ReNeg: Learning Negative Embedding with Reward Guidance
RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds
RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance
Reproducible Vision-Language Models Meet Concepts Out of Pre-Training
Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation
Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation
ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge
ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
Resilient Sensor Fusion Under Adverse Sensor Failures via Multi-Modal Expert Fusion
ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
RestorGS: Depth-aware Gaussian Splatting for Efficient 3D Scene Restoration
Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation
Rethinking Correspondence-based Category-Level Object Pose Estimation
Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention
Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting
Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection
Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment
Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification
Rethinking Query-based Transformer for Continual Image Segmentation
Rethinking Reconstruction and Denoising in the Dark: New Perspective, General Architecture and Beyond
Rethinking RoI Strategy in Interactive 3D Segmentation for Medical Images
Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers
Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
Re-thinking Temporal Search for Long-Form Video Understanding

« prev Page 43/59 next »