#scene-understanding Repositories
Discover 13 active open source GitHub repositories tagged with #scene-understanding, accumulating 20,151 total stars (averaging 1,550 stars per project). Leading this topic is manycore-research/SpatialLM with 5,165 stars.
13 repositories total
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.
This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! ๐ฅ
A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer
Lightweight models for real-time semantic segmentation on PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.github.io/
Frequently Asked Questions
What is the most popular #scene-understanding repository on GitHub?
The top ranked open source #scene-understanding project on GitHub is manycore-research/SpatialLM with 5,165 stars. [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
Which programming languages are most used in #scene-understanding repositories?
Among the top ranked #scene-understanding projects on GitHub, the most common programming languages are Python, Jupyter Notebook, JavaScript, C#.
How is the #scene-understanding repository ranking calculated?
We track 13 active open source repositories tagged with #scene-understanding (500+ stars), totaling 20,151 stars with an average of 1,550 stars per repository. Rankings update daily from the GitHub API.