3d-scene-understanding

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Official implementation of CVPR23 paper "Diffusion-based Generation, Optimization, and Planning in 3D Scenes"

(CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

[IROS2024] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

Awesome OVD-OVS - A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future

[CVPR 2025, Highlight] CrossOver: 3D Scene Cross-Modal Alignment

🔥GrowSP in PyTorch (CVPR 2023)

[CVPR 2024] Symphonies (Scene-from-Insts): Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

An SDK for multi-agent collaborative perception.

SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation (3DV 2025)

Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

Official implementation of the NeurIPS22 paper "HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes"

The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'

[CVPR 2024] Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships

An Efficient, Flexible, and General deep learning framework that retains minimal.

[ICLR 2024] AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation