ICCV

Computer Vision

9,145 papers · 2013–2025

ICCV (International Conference on Computer Vision) is a leading computer vision venue covering recognition, reconstruction, and visual learning.

Papers per year

454

526

621

1,075

1,612

2,156

2,701

'15

'25

Top authors

Luc Van Gool 74 papers

Yi Yang 65 papers

Lei Zhang 60 papers

Ming-Hsuan Yang 50 papers

Marc Pollefeys 49 papers

Xiaogang Wang 45 papers

Jiwen Lu 44 papers

Jiaya Jia 44 papers

Cordelia Schmid 43 papers

Jie Zhou 43 papers

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their counts at this venue are combined. How identity is handled.

Newest papers

Task-Oriented Human Grasp Synthesis via Context- and Task-Aware Diffusers 2025

Scoring, Remember, and Reference: Catching Camouflaged Objects in Videos 2025

SP2T: Sparse Proxy Attention for Dual-stream Point Transformer 2025

ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting 2025

UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images 2025

TACO: Taming Diffusion for in-the-wild Video Amodal Completion 2025

Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection 2025

Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer 2025

AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation 2025

Blind Video Super-Resolution based on Implicit Kernels 2025

Underwater Visual SLAM with Depth Uncertainty and Medium Modeling 2025

Zero-Shot Composed Image Retrieval via Dual-Stream Instruction-Aware Distillation 2025

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion 2025

Secure On-Device Video OOD Detection Without Backpropagation 2025

Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification 2025

CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy 2025

PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction 2025

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image 2025

Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder 2025

Agreement aware and dissimilarity oriented GLOM 2025

All ICCV 2025 papers →