CVPR 2026

3,659 papers

Top Research Directions

Research directions most represented by CVPR 2026 papers.

Generalizing from Synthetic Data to the Real World 54
Overcoming the Static Scene Assumption 47
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 39
Scaling Visual Attention Beyond Quadratic Complexity 37
Mitigating Multi View Inconsistency in Generative 3D Modeling 35
The Spatial Reasoning Bottleneck in Multimodal Models 35
Aligning Global Semantics with Local Spatial Precision 33
The Decoupling of Visual Perception and Logical Reasoning 31
Aligning Video Generation Models with Physical Laws 29
Spatial Attention Masking in Generative Diffusion Models 29
Overcoming the Iterative Inference Latency of Diffusion Models 28
Physics Constrained Generative Human Motion Synthesis 26
Fusing 2D Semantic Features with 3D Geometric Representations 26
Group Relative Policy Optimization for Large Reasoning Models 25
Exploiting Temporal Redundancy in Video Neural Networks 24

Top Authors

AuthorPapers
Honglu Zhou4
Caiming Xiong3
Juan Carlos Niebles3
Junhao Chen3
Ramesh Raskar3
Siddharth Somasundaram3
silvio savarese3
Yanwei Fu3
Akshat Dave2
Andrew Zisserman2
Botong Wu2
Dahua Lin2
Di Wu2
Fangneng Zhan2
Gaowen Liu2
Gim Hee Lee2
Hanming Deng2
Hanspeter Pfister2
Hui Shan2
Jian Zhang2

Papers

Title
Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
Regulating Rather than Constraining: Adaptive Guidance for Complex Spectral Reconstruction in Pansharpening
RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model
Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model
ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers
Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
Reinforcing Structured Chain-of-Thought for Video Understanding
Reinforcing Video Object Segmentation to Think before it Segments
Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference
ReLaGS: Relational Language Gaussian Splatting
Relational Visual Similarity
ReLaX: Reasoning with Latent Exploration for Large Reasoning Models
Reliable Policy Transfer for Safety-Aware End-to-End Driving with Deep Reinforcement Learning
Reliev3R: Relieving Feed-forward 3D Reconstruction from Multi-View Geometric Annotations
Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views
RelightAnyone: A Generalized Relightable 3D Gaussian Head Model
Relightful Video Portrait Harmonization
REL-SF4PASS: Panoramic Semantic Segmentation with REL Depth Representation and Spherical Fusion
Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
ReMatch: Boosting Representation through Matching for Multimodal Retrieval
RemedyGS: Defend 3D Gaussian Splatting Against Computation Cost Attacks
Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
ReMoE: Region-Mixture Experts for Adversarially-Robust Vision Transformers
ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework
ReMoT: Reinforcement Learning with Motion Contrast Triplets
RenderFlow: Single-Step Neural Rendering via Flow Matching
Render-to-Adapt: Unsupervised Personal Adaptation for Gaze Estimation
Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery
Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models
Repurposing 3D Generative Model for Autoregressive Layout Generation
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
ResCa: Residual Caching for Diffusion Transformers Acceleration
ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes
Residual Connections Harm Generative Representation Learning
Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
Residual Diffusion Bridge Model for Image Restoration
Residual Primitive Fitting of 3D Shapes with SuperFrusta
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment
Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
Resolving the Identity Crisis in Text-to-Image Generation
Resolving the Stability-Plasticity Dilemma in Reinforcement Learning via Complementary Continual Critics
Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration
Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
RetFormer: Multimodal Retrieval for Enhancing Image Recognition
Rethinking 2D-3D Registration: A Novel Network for High-Value Zone Selection and Representation Consistency Alignment

« prev Page 52/74 next »