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.
Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)
| Date | Stars |
|---|---|
| 2026-07-24 | 1027 |
| 2026-07-25 | 1027 |
| 2026-07-28 | 1027 |
| 2026-07-30 | 1027 |
| 2026-08-10 | 1029 |
| 2026-08-19 | 1029 |
| 2026-08-23 | 1030 |
| 2026-09-03 | 1029 |
| 2026-09-06 | 1030 |
| 2026-09-14 | 1031 |
| 2026-09-15 | 1032 |
| 2026-09-20 | 1032 |
Today
— stars today
This week
+2 stars this week
This month
+3 stars this month
Momentum
0.0
growth rate 0.19%/day
# Segment Anything🤖️ in 3D with NeRFs (SA3D) ### [Project Page](https://jumpat.github.io/SA3D/) | [Arxiv Paper](https://arxiv.org/abs/2304.12308) | [Data (Google Drive)](https://drive.google.com/file/d/1iiW3EyhiL10U_FCJ0esSrvnzZkHguQ7V/view?usp=share_link) [Segment Anything in 3D with NeRFs](https://arxiv.org/abs/2304.12308) [Jiazhong Cen](https://github.com/Jumpat)<sup>1\*</sup>, [Zanwei Zhou](https://github.com/Zanue)<sup>1\*</sup>, [Jiemin Fang](https://jaminfong.cn/)<sup>2,3†</sup>, [Chen Yang](https://github.com/chensjtu)<sup>1</sup>, [Wei Shen](https://shenwei1231.github.io/)<sup>1✉</sup>, [Lingxi Xie](http://lingxixie.com/)<sup>2</sup>, [Dongsheng Jiang](https://sites.google.com/site/dongshengjiangbme/)<sup>2</sup>, [Xiaopeng Zhang](https://sites.google.com/site/zxphistory/)<sup>2</sup>, [Qi Tian](https://scholar.google.com/citations?hl=en&user=61b6eYkAAAAJ)<sup>2</sup> <sup>1</sup>AI Institute, SJTU   <sup>2</sup>Huawei Inc   <sup>3</sup>School of EIC, HUST . \*denotes equal contribution †denotes project lead. *Given a NeRF, just input prompts from **one single view** and then get your 3D model.* <img src="imgs/SA3D.gif" width="800"> We propose a novel framework to Segment Anything in 3D, named <b>SA3D</b>. Given a neural radiance field (NeRF) model, SA3D allows users to obtain the 3D segmentation result of any target object via only <b>one-shot</b> manual prompting in a single rendered view. The entire process for obtaining the target 3D model can be completed in approximately 2 minutes, yet without any engineering optimization. Our experiments demonstrate the effectiveness of SA3D in different scenes, highlighting the potential of SAM in 3D scene perception. ## Update * **2025/04/03**: We are excited to release a new [dataset](https://drive.google.com/file/d/1iiW3EyhiL10U_FCJ0esSrvnzZkHguQ7V/view?usp=share_link) for 3D segmentation based on 3D Gaussian Splatting (3D-GS). The dataset features challenging scenes with severe occlusions, reflective surfaces, and multi-granularity segmentation. We warmly welcome the community to explore and use it! * **2024/04/16**: We release the [3D-GS](https://github.com/graphdeco-inria/gaussian-splatting) version of SA3D ([here](https://github.com/Jumpat/SegmentAnythingin3D/tree/nerfstudio-version)). Now 3D segmentation can be achieved within seconds! * **2023/11/11**: We release the [nerfstudio](https://docs.nerf.studio) version of SA3D ([here](https://github.com/Jumpat/SegmentAnythingin3D/tree/nerfstudio-version))! Currently it only supports the text prompt as input. * **2023/06/29**: We now support [MobileSAM](https://github.com/ChaoningZhang/MobileSAM) as the segmentation network. Follow the installation instruction in [MobileSAM](https://github.com/ChaoningZhang/MobileSAM), and then download *mobile_sam.pt* into folder ``./dependencies/sam_ckpt``. You can use `--mobile_sam` to switch to MobileSAM. ## Overall Pipeline  With input prompts, SAM cuts out the target object from the according view. The obtained 2D segmentation mask is projected onto 3D mask grids via density-guided inverse rendering. 2D masks from other views are then rendered, which are mostly uncompleted but used as cross-view self-prompts to be fed into SAM again. Complete masks can be obtained and projected onto mask grids. This procedure is executed via an iterative manner while accurate 3D masks can be finally learned. SA3D can adapt to various radiance fields effectively without any additional redesigning. ## Installation ``` git clone https://github.com/Jumpat/SegmentAnythingin3D.git cd SegmentAnythingin3D conda create -n sa3d python=3.10 conda activate sa3d pip install -r requirements.txt ``` ### SAM and Grounding-DINO: ``` # Installing SAM mkdir dependencies; cd dependencies mkdir sam_ckpt; cd sam_ckpt wget https://dl.fbaipublicfiles.com/segment_anything/sam
Excerpt of 9,048 characters
Read on GitHub
38
20
3
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:cab3eb39483e8ef7, topic:computer-vision, topic:nerf, readme:gaussian splatting
matched fp:cab3eb39483e8ef7, topic:deep-learning