iccv2021 开源项目推荐（116 个）

amusi /ICCV2025-Papers-with-Code

ICCV 2025 论文和开源项目合集

extreme-assistant /ICCV2023-Paper-Code-Interpretation

ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理

yuval-alaluf /restyle-encoder

Official Implementation for "ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement" (ICCV 2021) https://arxiv.org/abs/2104.02699

microsoft /SoftTeacher

半监督学习、目标检测、ICCV2021

yuxumin /PoinTr

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

bupt-ai-cz /LLVIP

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

rundiwu /DeepCAD

code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

EndlessSora /focal-frequency-loss

[ICCV 2021]图像重建与合成中的焦频损耗

alex04072000 /FuSta

Hybrid Neural Fusion for Full-frame Video Stabilization

cuiaiyu /dressing-in-order

(ICCV'21) Official code of "Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing." (No longer actively maintained)

jiaxi-jiang /FBCNN

ICCV 2021 论文《Towards Flexible Blind JPEG Artifacts Removal (FBCNN)》的官方代码

jychoi118 /ilvr_adm

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (ICCV 2021 Oral)

jeffffffli /res-loglikelihood-regression

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

eliahuhorwitz /DeepSIM

论文的官方PyTorch实现：“DeepSIM：从单一增强训练样本进行图像形状操作”（ICCV 2021口头报告）

wvangansbeke /Unsupervised-Semantic-Segmentation

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals. [ICCV 2021]

Atten4Vis /ConditionalDETR

This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)

zhejz /carla-roach

Roach: End-to-End Urban Driving by Imitating a Reinforcement Learning Coach. ICCV 2021.

henghuiding /Vision-Language-Transformer

[ICCV2021 & TPAMI2023] Vision-Language Transformer and Query Generation for Referring Segmentation

fcjian /TOOD

TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

raywzy /ICT

High-Fidelity Pluralistic Image Completion with Transformers (ICCV 2021)