facebookresearch / univlgLinks
Unifying 2D and 3D Vision-Language Understanding
☆111Updated 3 months ago
Alternatives and similar repositories for univlg
Users that are interested in univlg are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding☆95Updated 8 months ago
- SceneFun3D ToolKit☆157Updated 6 months ago
- Official implementation of the paper "Unifying 3D Vision-Language Understanding via Promptable Queries"☆81Updated last year
- [CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding☆115Updated 5 months ago
- Code&Data for Grounded 3D-LLM with Referent Tokens☆127Updated 9 months ago
- Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆85Updated 2 months ago
- From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perceptio…☆59Updated 2 weeks ago
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆281Updated last month
- [NeurIPS 2024] Official code repository for MSR3D paper☆64Updated 2 months ago
- [ICLR 2025] Official code of "Segment any 3D Object with Language"☆52Updated 2 weeks ago
- ☆51Updated last year
- [CVPR 2024] Situational Awareness Matters in 3D Vision Language Reasoning☆42Updated 10 months ago
- [3DV 2025] Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model☆103Updated 4 months ago
- [CVPR 2024] Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding☆57Updated last year
- ☆92Updated 9 months ago
- [RAL 2024] OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding☆28Updated 8 months ago
- The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'☆145Updated 2 weeks ago
- Code of 3DMIT: 3D MULTI-MODAL INSTRUCTION TUNING FOR SCENE UNDERSTANDING☆31Updated last year
- [ICLR 2025] SPA: 3D Spatial-Awareness Enables Effective Embodied Representation☆167Updated 4 months ago
- [NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.☆181Updated last week
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS2024)☆84Updated 3 weeks ago
- [ECCV 2024] Empowering 3D Visual Grounding with Reasoning Capabilities☆80Updated last year
- [ECCV2024] Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding☆124Updated last year
- OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models☆67Updated 3 weeks ago
- [CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding☆178Updated 6 months ago
- [NeurIPS 2023] Weakly Supervised 3D Open-vocabulary Segmentation☆122Updated last year
- [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.☆168Updated 4 months ago
- Official implementation of DepthLM☆229Updated 2 weeks ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆156Updated 2 weeks ago
- [CVPR 2025] 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer☆72Updated 4 months ago