Alternatives and similar repositories for track_on

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

• cvlab-kaist / locotrack
  Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)
  ☆191Updated 3 months ago
• TonyLianLong / RCF-UnsupVideoSeg
  [CVPR 2023] Segmenting objects in videos without human annotations 🤯: Official implementation for Bootstrapping Objectness from Videos b…
  ☆37Updated last year
• TimSong412 / OmniTrackFast
  Official Code For Track Everything Everywhere Fast and Robustly
  ☆67Updated 4 months ago
• serycjon / MFT
  MFT: Long-Term Tracking of Every Pixel -- code for the WACV 2024 paper
  ☆61Updated 8 months ago
• ywyue / FiT3D
  [ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning
  ☆286Updated 5 months ago
• SpatialVision / Prior-Depth-Anything
  ☆282Updated 2 months ago
• ayshrv / gmrw
  Official PyTorch implementation of Self-Supervised Any-Point Tracking by Contrastive Random Walks, ECCV 2024.
  ☆52Updated 9 months ago
• YunzeMan / Lexicon3D
  [NeurIPS 2024] Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
  ☆95Updated 6 months ago
• aim-uofa / FrozenRecon
  [ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models
  ☆128Updated 11 months ago
• qianduoduolr / DecoMotion
  [ECCV 2024] Decomposition Betters Tracking Everything Everywhere
  ☆113Updated last year
• lyclyc52 / SANeRF-HQ
  [CVPR2024] SANeRF-HQ: Segment Anything for NeRF in High Quality.
  ☆50Updated last year
• google-deepmind / omninocs
  A large-scale NOCS dataset.
  ☆90Updated last year
• Davidyao99 / uni4d
  [CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
  ☆184Updated 2 months ago
• ShngJZ / WildCamera
  Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
  ☆79Updated last year
• OpenDriveLab / DetAny3D
  [ICCV 2025] Detect Anything 3D in the Wild
  ☆163Updated last month
• princeton-vl / WAFT
  ☆65Updated last month
• Michaelszj / pro-tracker
  ☆81Updated 6 months ago
• crockwell / far
  [CVPR 2024 - Highlight] FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation
  ☆134Updated 4 months ago
• heyoeyo / muggled_dpt
  Muggled DPT: Depth estimation without the magic
  ☆101Updated 3 months ago
• lorebianchi98 / Talk2DINO
  [ICCV2025] Official repository of the paper "Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary…
  ☆60Updated this week
• princeton-vl / OMNI-DC
  [ICCV 25] Official code for "OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration"
  ☆56Updated last month
• Sungmin-Woo / ProDepth
  [ECCV 2024] ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
  ☆34Updated 6 months ago
• zlai0 / TrackTention
  ☆23Updated 4 months ago
• VITA-Group / VLM-3R
  VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
  ☆235Updated last week
• YihongSun / Dynamo-Depth
  [NeurIPS 2023] Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
  ☆84Updated 7 months ago
• zhyever / PatchRefiner
  [ECCV 2024] Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation
  ☆59Updated 7 months ago
• facebookresearch / UnSAMFlow
  Source code for CVPR 2024 paper UnSAMFlow Unsupervised Optical Flow Guided by Segment Anything Model.
  ☆103Updated last year
• snap-research / DELTA_densetrack3d
  DELTA: Dense Efficient Long-range 3D Tracking for Any video (ICLR 2025)
  ☆119Updated 4 months ago
• andrehuang / loftup
  [ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"
  ☆179Updated 2 weeks ago
• peoplelu / SAS
  [ICCV 2025] SAS: Segment Any 3D Scene with Integrated 2D Priors
  ☆22Updated last month