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.
[ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
| Date | Stars |
|---|---|
| 2026-07-24 | 796 |
| 2026-07-25 | 796 |
| 2026-07-28 | 796 |
| 2026-07-30 | 796 |
| 2026-08-10 | 800 |
| 2026-08-19 | 799 |
| 2026-08-20 | 800 |
| 2026-08-21 | 801 |
| 2026-08-26 | 802 |
| 2026-08-27 | 804 |
| 2026-08-29 | 805 |
| 2026-09-01 | 804 |
| 2026-09-03 | 806 |
| 2026-09-04 | 806 |
| 2026-09-06 | 807 |
| 2026-09-07 | 808 |
| 2026-09-15 | 809 |
| 2026-09-17 | 810 |
| 2026-09-20 | 812 |
Today
+2 stars today
This week
+4 stars this week
This month
+11 stars this month
Momentum
0.0
growth rate 0.50%/day
<!-- PROJECT LOGO -->
<p align="center">
<h1 align="center">[ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos</h1>
<p align="center">
<a href="https://linjohnss.github.io/"><strong>Chin-Yang Lin</strong></a>
·
<a href="https://sunset1995.github.io/"><strong>Cheng Sun</strong></a>
·
<a href="https://fuenyang1127.github.io/"><strong>Fu-En Yang</strong></a>
<br>
<a href="https://minhungchen.netlify.app/"><strong>Min-Hung Chen</strong></a>
.
<a href="https://sites.google.com/site/yylinweb/"><strong>Yen-Yu Lin</strong></a>
·
<a href="https://yulunalexliu.github.io/"><strong>Yu-Lun Liu</strong></a>
</p>
<h3 align="center"><a href="https://linjohnss.github.io/longsplat">Project Page</a> | <a href="http://arxiv.org/abs/2508.14041">Paper</a> | <a href="https://drive.google.com/drive/folders/1b-QgNzWVpDaYkHQf3ycKORd7s5WekjGa?usp=drive_link">Evaluation Results</a></h3>
<div align="center"></div>
</p>
<p align="center">
<a href="">
<img src="./assets/teaser.gif" alt="Logo" width="90%">
</a>
</p>
## Overview
LongSplat is an unposed 3D Gaussian Splatting framework for robust reconstruction from casually captured long videos. Featuring incremental joint optimization, pose estimation with MASt3R, and adaptive octree anchoring, LongSplat achieves high-quality novel view synthesis from free viewpoints while remaining memory-efficient and scalable.
<p align="center">
<a href="">
<img src="./assets/teaser.png" alt="Logo" width="100%">
</a>
</p>
## News
⚠️ **2025.12.10**: Fixed training and eval pipeline for reproduction results.
🎉 **2025.08.27**: Release converter to 3DGS format for compatibility with general 3DGS viewers. See [Convert to 3DGS Format](#convert-to-3dgs-format) section.
🎉 **2025.08.20**: Code release!
## Installation
1. Clone LongSplat.
```bash
git clone --recursive https://github.com/NVlabs/LongSplat.git
cd LongSplat
```
2. Create the environment
```bash
conda create -n longsplat python=3.10.13 cmake=3.14.0 -y
conda activate longsplat
conda install pytorch torchvision pytorch-cuda=12.1 -c pytorch -c nvidia # use the correct version of cuda for your system
pip install -r requirements.txt
pip install submodules/simple-knn
pip install submodules/diff-gaussian-rasterization
pip install submodules/fused-ssim
```
3. Optional but highly suggested, compile the cuda kernels for RoPE (as in CroCo v2).
```bash
# DUST3R relies on RoPE positional embeddings for which you can compile some cuda kernels for faster runtime.
cd submodules/mast3r/dust3r/croco/models/curope/
python setup.py build_ext --inplace
cd ../../../../../../
```
## Dataset Preparation
DATAROOT is `./data` by default. Please first make data folder by `mkdir data`.
### Free Dataset
Download Free dataset from [Dropbox](https://www.dropbox.com/sh/jmfao2c4dp9usji/AAC7Ydj6rrrhy1-VvlAVjyE_a?dl=0), and save it into the `./data/free` folder.
### Hike Dataset
Download Hike dataset from [Google Drive](https://drive.google.com/drive/folders/1kGY-VijIbXNsNb7ghEywi1fvkH4BaIEz?usp=share_link), and save it into the `./data/hike` folder.
### Tanks and Temples
Download the data preprocessed by [Nope-NeRF](https://github.com/ActiveVisionLab/nope-nerf/?tab=readme-ov-file#Data) as below, and the data is saved into the `./data/tanks` folder.
```bash
wget https://www.robots.ox.ac.uk/~wenjing/Tanks.zip
```
<!-- ### CO3D
Download our preprocessed [data](https://ucsdcloud-my.sharepoint.com/:u:/g/personal/yafu_ucsd_edu/EftJV9Xpn0hNjmOiGKZuzyIBW5j6hAVEGhewc8aUcFShEA?e=x1aXVx), and put it saved into the `./data/co3d` folder. -->
## Run
### Training and Evaluation
The training scripts include both training, rendering, and evaluation steps:
Each `.sh` script runs three main Python scripts in sequence:
- `train.py`: Trains the LongSplat model
- `render.py`: Renders the trained model to generate novel views
- `metrics.py`: Evaluates the rendering quality and computes metrics
```baExcerpt of 6,723 characters
Read on GitHub
14
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9549569de22fb715, topic:computer-vision, topic:3d-reconstruction, readme:pose estimation