Alternatives and similar repositories for SAM2-Docker

Users that are interested in SAM2-Docker are comparing it to the libraries listed below

• patrick-tssn / Streaming-Grounded-SAM-2
  Grounded Tracking for Streaming Videos
  ☆123Updated last year
• yuliangguo / depth_any_camera
  [CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera
  ☆257Updated last month
• pablovela5620 / sam2-depthanything
  ☆76Updated 7 months ago
• cake-lab / HybridDepth
  Official implementation for HybridDepth Model [WACV 2025, ISMAR 2024]
  ☆170Updated 4 months ago
• heyoeyo / muggled_sam
  Muggled SAM: Segmentation without the magic
  ☆171Updated 2 weeks ago
• spacewalk01 / depth-anything-tensorrt
  C++ TensorRT implementation of Depth-Anything V1, V2
  ☆436Updated 8 months ago
• junhong-3dv / s2m2
  Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"
  ☆119Updated this week
• safouaneelg / FusionVision
  Official implementation of the paper " FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cam…
  ☆110Updated last month
• aminebdj / OpenYOLO3D
  [ICLR 2025 (Oral 📢) ] Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet2…
  ☆228Updated 8 months ago
• Aradhye2002 / EcoDepth
  [CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"
  ☆198Updated last week
• Jyxarthur / flowsam
  [ACCV 2024 (Oral)] Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi …
  ☆322Updated 11 months ago
• naver / must3r
  MUSt3R: Multi-view Network for Stereo 3D Reconstruction
  ☆271Updated last month
• facebookresearch / efm3d
  This is the official release for the paper "EFM3D A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models" (https//arx…
  ☆163Updated last month
• Jianxff / droid_metric
  run DROID-SLAM with Metric3D to improve monocular performance
  ☆164Updated last year
• heyoeyo / muggled_dpt
  Muggled DPT: Depth estimation without the magic
  ☆109Updated last week
• autodistill / autodistill-grounded-sam-2
  Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
  ☆134Updated last year
• ais-lab / pl2map
  [IROS 2024] Representing 3D sparse map points and lines for camera relocalization; [IROS 2025] Improved 3D Point-Line Mapping Regression …
  ☆221Updated 4 months ago
• Nightmare-n / DepthAnyVideo
  Depth Any Video with Scalable Synthetic Data (ICLR 2025)
  ☆508Updated 11 months ago
• wrchen530 / leapvo
  [CVPR 2024] LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry
  ☆236Updated 7 months ago
• AssafSinger94 / dino-tracker
  Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
  ☆531Updated last year
• Michaelszj / pro-tracker
  ☆87Updated 10 months ago
• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆266Updated 7 months ago
• huiyu-gao / VisFusion
  [CVPR 2023] Code for "VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos"
  ☆188Updated last year
• hujiecpp / PE3R
  PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start explorin…
  ☆391Updated 7 months ago
• IDEA-Research / TAPTR
  [ECCV 2024 & NeurIPS 2024] Official implementation of the paper TAPTR & TAPTRv2 & TAPTRv3
  ☆268Updated 11 months ago
• cvlab-kaist / locotrack
  Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)
  ☆201Updated 7 months ago
• OpenMask3D / openmask3d
  ☆242Updated last year
• M2219 / ESMStereo
  The ESMStereo models are designed with low computational complexity to achieve an acceptable balance between accuracy and speed, which ma…
  ☆55Updated 3 months ago
• prs-eth / RollingDepth
  [CVPR 2025] RollingDepth: Video Depth without Video Models
  ☆590Updated 8 months ago
• qianduoduolr / DecoMotion
  [ECCV 2024] Decomposition Betters Tracking Everything Everywhere
  ☆112Updated last year