Pointcept / SegmentAnything3D
[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes
☆1,008Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for SegmentAnything3D
- Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.☆551Updated last year
- [CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies☆658Updated last year
- Segment Anything in 3D with NeRFs (NeurIPS 2023)☆893Updated 5 months ago
- [CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation☆342Updated 3 weeks ago
- [CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)☆808Updated 7 months ago
- [ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds☆649Updated 3 weeks ago
- Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]☆677Updated 6 months ago
- [NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models☆571Updated 11 months ago
- Segment Any RGBD☆790Updated last year
- Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Tra…☆626Updated this week
- [ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI☆489Updated 10 months ago
- Segment-Anything + 3D. Let's lift anything to 3D.☆1,556Updated last year
- Point-NeRF: Point-based Neural Radiance Fields☆1,096Updated 8 months ago
- [CVPR 2023 Highlight] Neural Kernel Surface Reconstruction☆778Updated last month
- [NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies☆794Updated 11 months ago
- The official implementation of SAGA (Segment Any 3D GAussians)☆597Updated 5 months ago
- ☆435Updated 4 months ago
- [CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".☆360Updated 4 months ago
- Code & Models for 3DETR - an End-to-end transformer model for 3D object detection☆627Updated 2 years ago
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆385Updated 6 months ago
- [CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration☆672Updated 11 months ago
- [ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.☆669Updated 4 months ago
- [NeurIPS'22] An official PyTorch implementation of PTv2.☆356Updated last year
- The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foun…☆1,428Updated 2 weeks ago
- We extend Segment Anything to 3D perception by combining it with VoxelNeXt.☆540Updated last year
- Code for LERF: Language Embedded Radiance Fields☆668Updated 4 months ago
- [CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling☆541Updated 11 months ago
- Point-SAM: This is the official repository of "Point-SAM: Promptable 3D Segmentation Model for Point Clouds". We provide codes for runnin…☆138Updated 3 months ago
- This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.☆690Updated last year
- A shift-window based transformer for 3D sparse tasks☆213Updated last year