Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis
| Date | Stars |
|---|---|
| 2026-07-24 | 803 |
| 2026-07-25 | 803 |
| 2026-07-28 | 803 |
| 2026-07-30 | 803 |
| 2026-08-06 | 803 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <p align="center"> <img src="fig/logo.png" width="100px"> </p> [](https://arxiv.org/abs/2311.10959) [](https://zhuanlan.zhihu.com/p/702702109) [](https://www.youtube.com/watch?v=oVVUaBY61eo) <h2> A Toolbox for Sparse-View X-ray 3D Reconstruction </h2> <img src="3d_demo/backpack.gif" style="height:260px" /> <img src="3d_demo/box.gif" style="height:260px" /> <img src="3d_demo/bonsai.gif" style="height:260px" /> <img src="3d_demo/foot.gif" style="height:230px" />     <img src="3d_demo/teapot.gif" style="height:230px" /> <img src="3d_demo/engine.gif" style="height:230px" /> </div> ### Introduction This repo is a comprehensive toolbox and library for X-ray 3D reconstruction including two tasks, novel view synthesis (NVS) and computed tomography (CT) reconstruction. This repo supports 12 state-of-the-art methods including six NeRF-based methods, three 3DGS-based methods, two optimization-based methods, and one analytical method. We also provide code for fancy visualization such as turntable video and data generation to help your research. If you find this repo useful, please give it a star ⭐ and consider citing our paper. Thank you. ### News - **2026.06.18 :** Our new work [Perturbed-Gaussian-Ensemble](https://arxiv.org/abs/2603.06852) for active learning 3DGS-based CT reconstruction has been accepted by ECCV 2026. Congrats to [Yulun](https://github.com/yulunwu0108/Perturbed-Gaussian-Ensemble). Code and models will be released at [this repo](https://github.com/yulunwu0108/Perturbed-Gaussian-Ensemble). 🚀 - **2025.09.18 :** Our new work [CARE](https://arxiv.org/abs/2506.02093) for diffusion based Anatomy-aware enhancement of sparse-view CT reconstruction has been accepted by NeurIPS 2025. Congrats to [Tianyu](https://lin-tianyu.github.io/). Code and models have been released at [this repo](https://github.com/MrGiovanni/CARE). 🍒 - **2025.06.25 :** Our new work [X2-Gaussian](https://arxiv.org/abs/2503.21779) for dynamic human chest breathing CT reconstruction has been accepted by ICCV 2025. Congrats to [Weihao](https://yuyouxixi.github.io/). Code and models will be released at [this repo](https://github.com/yuyouxixi/x2-gaussian). 🚀 - **2024.09.25 :** Our new work [R2-Gaussian](https://arxiv.org/abs/2405.20693v1) has been accepted by NeurIPS 2024. Congrats to [Ruyi](https://ruyi-zha.github.io/). Code and model will be released at [this repo](https://github.com/Ruyi-Zha/r2_gaussian). 💫 - **2024.09.01 :** Code of our ECCV 2024 work [X-Gaussian](https://github.com/caiyuanhao1998/X-Gaussian/) has been released. Welcome to have a try! 🚀 - **2024.07.09 :** Our SAX-NeRF has been added to the [Awesome-Transformer-Attention](https://github.com/cmhungsteve/Awesome-Transformer-Attention/blob/main/README_2.md) collection 💫 - **2024.06.16 :** I will present this work in person. Our poster session is from 10:30 am to 00:30 pm, Jun 20 at Arch 4A-E Poster #147. Welcome to chat with me in Seattle Convention Center. :satisfied: - **2024.06.16 :** More raw data and generation samples are provided. Feel free to use them. - **2024.06.03 :** Code for traditional methods has been released. 🚀 - **2024.06.03 :** Code for fancy visualization and data generation has been released. 🚀 - **2024.06.02 :** Data, code, models, and training logs have been released. Feel free to use them :) - **2024.03.07 :** Our new work [X-Gaussian](https://github.com/caiyuanhao1998/X-Gaussian), the first 3DGS-based method for X-ray imaging, is now on [arxiv](https://arxiv.org/abs/2403.04116) now. Code, models, and training logs will be released at [this repo](https://github.com/caiyuanhao1998/X-Gaussian). Stay tuned. 💫 - **2024.02.26 :** Our paper has been accepted by CVPR 2024. Code and pre-trained models will be released to the public before
Excerpt of 12,991 characters
Read on GitHub
Yuanhao Cai · Johns Hopkins University <- Tsinghua · United States
70
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0b0e13a813b5ce34, topic:nerf, topic:3d-reconstruction, desc:3d reconstruction