Alternatives and similar repositories for SegmentAnything3D:

Users that are interested in SegmentAnything3D are comparing it to the libraries listed below

• pengsongyou / openscene
  [CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
  ☆708Updated last year
• JonasSchult / Mask3D
  Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
  ☆609Updated last year
• filaPro / oneformer3d
  [CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation
  ☆434Updated 5 months ago
• Jumpat / SegmentAnythingin3D
  Segment Anything in 3D with NeRFs (NeurIPS 2023)
  ☆935Updated 2 weeks ago
• Pointcept / PointTransformerV3
  [CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
  ☆1,092Updated 3 weeks ago
• youquanl / Segment-Any-Point-Cloud
  [NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
  ☆611Updated last year
• Jun-CEN / SegmentAnyRGBD
  Segment Any RGBD
  ☆823Updated last year
• Pointcept / Pointcept
  Pointcept: a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral), PPT (CVPR'24), …
  ☆2,052Updated last week
• zyc00 / Point-SAM
  [ICLR 2025] Point-SAM: Promptable 3D Segmentation Model for Point Clouds
  ☆250Updated 3 weeks ago
• guochengqian / PointNeXt
  [NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
  ☆865Updated last year
• Anything-of-anything / Anything-3D
  Segment-Anything + 3D. Let's lift anything to 3D.
  ☆1,594Updated last year
• OpenRobotLab / PointLLM
  [ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds
  ☆762Updated 5 months ago
• baaivision / Uni3D
  [ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI
  ☆550Updated last year
• minghanqin / LangSplat
  Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]
  ☆779Updated 11 months ago
• salesforce / ULIP
  ☆490Updated 2 months ago
• drprojects / superpoint_transformer
  Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Tra…
  ☆763Updated last month
• ZrrSkywalker / Point-NN
  [CVPR 2023] Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
  ☆511Updated last year
• nv-tlabs / NKSR
  [CVPR 2023 Highlight] Neural Kernel Surface Reconstruction
  ☆822Updated 2 months ago
• dvlab-research / 3D-Box-Segment-Anything
  We extend Segment Anything to 3D perception by combining it with VoxelNeXt.
  ☆549Updated 2 years ago
• qinzheng93 / GeoTransformer
  [CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration
  ☆742Updated last year
• NVlabs / VoxFormer
  Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]
  ☆1,107Updated last year
• YvanYin / Metric3D
  The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foun…
  ☆1,728Updated last month
• lkeab / gaussian-grouping
  [ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.
  ☆779Updated 9 months ago
• Pointcept / PointTransformerV2
  [NeurIPS'22] An official PyTorch implementation of PTv2.
  ☆380Updated last year
• facebookresearch / 3detr
  Code & Models for 3DETR - an End-to-end transformer model for 3D object detection
  ☆656Updated 2 years ago
• Jumpat / SegAnyGAussians
  The official implementation of SAGA (Segment Any 3D GAussians)
  ☆702Updated 3 weeks ago
• lpiccinelli-eth / UniDepth
  Universal Monocular Metric Depth Estimation
  ☆837Updated 3 weeks ago
• segments-ai / panoptic-segment-anything
  Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation
  ☆404Updated 11 months ago
• xuxw98 / ESAM
  [ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time
  ☆473Updated 2 weeks ago
• dvlab-research / VoxelNeXt
  VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (CVPR 2023)
  ☆779Updated last year