仓库只是论文索引，不含模型权重，需自行到各论文项目页获取代码与数据；在线检索依赖 Hugging Face Space，需能访问该站点；README 显示 ICCV 2025 论文收录进度仅约 2%，覆盖尚不完整
ICCV-2023-25-Papers
DmitryRyuminMIT长期未更新汇总 ICCV 2023–2025 三届顶会的计算机视觉论文，附代码链接，方便快速追踪 3D 重建、人脸识别等方向的最新研究。
ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!
v2025.10.27-rc.1发布于 2025-10-27 19:19 UTC973star49fork同步于 2026-11-07 07:30 UTC
git clone https://github.com/DmitryRyumin/ICCV-2023-25-Papers.git 硬件要求按 README 说明
README 未说明，纯论文清单仓库，无需 GPU 或显存
汇总 ICCV 2023-2025 论文与代码实现的 Awesome 清单，帮你快速跟进视觉前沿
汇总 ICCV 2023–2025 三届顶会的计算机视觉论文，附代码链接，方便快速追踪 3D 重建、人脸识别等方向的最新研究。
核心能力
- 按会议年份整理 ICCV 2023 至 2025 录用论文
- 标注论文对应的开源代码实现
- 提供 Hugging Face 在线检索应用 NewEraAI-Papers
- 用 GitHub Actions 自动解析 Markdown 并生成 JSON
- 附 ICCV 2025 官方会议日程与报告时间链接
容易踩的坑
内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README
- v2025.10.27-rc.1ICCV 2023-25 Papers - Release Candidate (v2025.10.27-rc.1)pre-release最新正式版2025-10-27 · 2025-10-27 19:19 UTC
ICCV 2023-25 Papers - Release Candidate (v2025.10.27-rc.1)
Overview
Dive into the latest cutting-edge research from the leading computer vision conference - ICCV 2025.
Each entry may include links to available resources:
- Paper on thecvf / arXiv
- Code on GitHub
- Models or demos on Hugging Face
- Supplementary media (e.g., YouTube)
Not all papers provide every resource - only the available badges are shown.
Highlights
Introduced new sections for ICCV 2025 Papers:
- Multi-Modal Learning
- Structure and Motion
- Efficient Learning
- View Synthesis and Scene Reconstruction
- Foundation Models and Representation Learning
- Human Modeling
- 3D Pose Understanding
- Vision + Graphics
- Applications and Evaluation
- Content Generation
- Physical Scene Perception
- Segmentation and Grouping
Full Changelog: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/commits/v2025.10.27-rc.1
Happy Researching!
用户点评
登录用户的真实使用记录，可按版本和硬件筛选共 0 条
还没有人点评。第一个说出真实体验的人最有价值。
ICCV 2025 Papers: Explore a comprehensive collection of cutting-edge research papers presented at ICCV 2025, the premier computer vision conference. Keep up to date with the latest advances in computer vision and deep learning. Code implementations included. :star: the repository for the development of visual intelligence!
[!TIP] The online version of the ICCV 2025 Conference Programme, comprises a list of all accepted full papers, their presentation order, as well as the designated presentation times.
[!important] Conference table will be up to date all the time.
Contributors
[!NOTE] Contributions to improve the completeness of this list are greatly appreciated. If you come across any overlooked papers, please feel free to create pull requests, open issues or contact me via email. Your participation is crucial to making this repository even better.
Papers-2025
Papers-2023
gaussian-splatting
graphdeco-inria·Python
3D Gaussian Splatting 的官方参考实现，用高斯点云做辐射场重建，实现实时可交互的逼真场景渲染。
3D高斯泼溅+43D 重建
24453+213.5k2025-10-17 14:28 UTC
instant-ngp
NVlabs·Cuda
用多分辨率哈希编码把 NeRF、SDF 等神经图形基元的训练从几小时压到几秒，实时渲染三维场景。
神经辐射场+43D 重建
17593+52.1kv2.02026-02-02 12:32 UTC
Open3D
isl-org·C++
Open3D 是一个现代 3D 数据处理库，提供点云、网格、RGB-D 和 3D 可视化等算法与工具，支持 C++ 和 Python，可用于 3D 感知、重建与机器学习研究。
3D数据处理+43D 重建
14193+122.6kv0.20.02026-11-10 19:59 UTC
colmap
colmap·C++
从多张照片重建三维场景的 C++ 工具，集成了运动恢复结构（SfM）和多视图立体（MVS），可输出相机位姿与稠密点云。
三维重建+43D 重建
13197+232.2kdatasets-eth3d-undistorted-v12026-11-10 08:51 UTC