This is a repo for paper "Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes". paper, project page
`bibtex @inproceedings{linghu20263d, title={3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding}, author={Linghu, Xiongkun and Huang, Jiangyong and Jia, Baoxiong and Huang, Siyuan}, booktitle={International Conference on Machine Learning}, year={2026} } `
We build a multi-modal large language model for 3D scene understanding, excelling in tasks such as 3D grounding, captioning, and question answering.
The main features of zzzzchs/chat-scene are: 3D Scene Understanding.
Open-source alternatives to zzzzchs/chat-scene include: anjiecheng/spatialrgpt — arxiv / Huggingface. baaivision/uni3d — Uni3D: Exploring Unified 3D Representation at Scale. chat-3d/chat-3d — This is a repo for paper "Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes".… djiajunustc/3d-llava — 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer. embodied-generalist/embodied-generalist — An Embodied Generalist Agent in 3D World. 3d-rft/3d-rft — ``bibtex @inproceedings{linghu20263d, title={3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene…
