Cancel
New
About
Go deeper
Ask Althea
Sign in with OpenReview
Press
⌘/
to show chat
Tiptree Systems
New
About
Sign in
Appearance
System
CVPR
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
Author
Papers
Honglu Zhou
4
Caiming Xiong
3
Juan Carlos Niebles
3
Junhao Chen
3
Ramesh Raskar
3
Siddharth Somasundaram
3
silvio savarese
3
Yanwei Fu
3
Akshat Dave
2
Andrew Zisserman
2
Botong Wu
2
Dahua Lin
2
Di Wu
2
Fangneng Zhan
2
Gaowen Liu
2
Gim Hee Lee
2
Hanming Deng
2
Hanspeter Pfister
2
Hui Shan
2
Jian Zhang
2
Papers
Title
OneHOI: Unifying Human-Object Interaction Generation and Editing
One Layer’s Trash is Another Layer’s Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
One-Shot Flow, Any-Time Frame: A Bidirectional Warping Framework for Event-Based Video Frame Interpolation
OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models
One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
OneThinker: All-in-one Reasoning Model for Image and Video
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model
Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision
OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
On the Role of Temporal Granularity in the Robustness of Spiking Neural Networks
On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles
Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments
OpenMMReasoner: Pushing the Frontiers in Multimodal Reasoning with an Open and General Recipe
OpenT2M: No-frill Motion Generation with Open-source, Large-scale, High-quality Data
Open the Motion Door: Atomic Motion Decomposition and Recomposition for Open-Vocabulary Motion Generation
OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness
OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding
Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation
OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation
Optical Diffraction-based Convolution for Semiconductor Lithography
Optical Flow Matching: Reframing Optical Flow as Continuous Transport Dynamics
OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives
OralGPT-Omni: A Versatile Dental Multimodal Large Language Model
OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis
OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
ORBIT: Benchmarking SfM in the Wild with 360° Video
Order Matters: 3D Shape Generation from Sequential VR Sketches
ORD: Object-Relation Decoupling for Generalized 3D Visual Grounding
ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models
OrienPose: Orientation-Guided Novel View Synthesis for Single-Image Unseen Object Pose Estimation
OrionEdit: Bridging Reference and Source Images for Generalized Cross-Image Editing
ORION: ORthonormal Text Encoding for Universal VLM AdaptatION
ORSATR-X: A Foundation Model based on Differential-and-Excitation Networks for Optical Remote Sensing Object Recognition
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
Orthogonal Spatial-Aware Multi-View Anchor Graph Clustering for Incomplete Remote Sensing Data
ORV: 4D Occupancy-centric Robot Video Generation
OSA: Echocardiography Video Segmentation via Orthogonalized State Update and Anatomical Prior-aware Feature Enhancement
« prev
Page 44/74
next »