CognitiveAISystems / 3DGraphLLMLinks
[ICCV 2025] 3DGraphLLM is a model that uses a 3D scene graph and an LLM to perform 3D vision-language tasks.
☆77Updated last month
Alternatives and similar repositories for 3DGraphLLM
Users that are interested in 3DGraphLLM are comparing it to the libraries listed below
Sorting:
- Unifying 2D and 3D Vision-Language Understanding☆104Updated last month
- [CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding☆113Updated 3 months ago
- Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)☆108Updated 10 months ago
- 4D Panoptic Scene Graph Generation (NeurIPS'23 Spotlight)☆114Updated 6 months ago
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS2024)☆83Updated this week
- [NeurIPS 2024] Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding☆95Updated 7 months ago
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆263Updated 2 weeks ago
- [CVPR 2024] Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding☆55Updated last year
- Improving 3D Large Language Model via Robust Instruction Tuning☆62Updated 6 months ago
- Code for the paper: "ODIN: A Single Model for 2D and 3D Segmentation" (CVPR 2024)☆162Updated 3 months ago
- [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.☆161Updated 3 months ago
- Code for "Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers" (NeurIPS 2024)☆194Updated 5 months ago
- [CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding☆171Updated 5 months ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆348Updated 2 months ago
- [ECCV2024] Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding☆124Updated last year
- [NeurIPS 2024] A Unified Framework for 3D Scene Understanding☆154Updated 2 months ago
- ☆50Updated 11 months ago
- Code of 3DMIT: 3D MULTI-MODAL INSTRUCTION TUNING FOR SCENE UNDERSTANDING