InternLM/Spatial-SSRL
[CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"
This project helps improve how Large Vision-Language Models (LVLMs) understand the spatial relationships between objects in images and videos. You input ordinary images or video clips, and the project enhances the model's ability to accurately describe locations, sizes, and relative positions without needing special labels. This is ideal for researchers and developers building or evaluating advanced AI vision systems.
116 stars.
Use this if you are a researcher or developer working with LVLMs and need to significantly boost their spatial reasoning capabilities efficiently and without extensive manual data annotation.
Not ideal if you need a plug-and-play application for immediate end-user tasks, as this is a framework for improving underlying model intelligence.
Stars
116
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/InternLM/Spatial-SSRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video