Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"
-
Updated
Oct 28, 2026 - Python
Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"
AllTracker is a model for tracking all pixels in a video.
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
Official repository for LiteTracker: Leveraging Temporal Causality for Accurate Low-latency Tissue Tracking; published at MICCAI 2025.
DELTA: Dense Efficient Long-range 3D Tracking for Any video (ICLR 2025)
The official implementation of "ETAP: Event-based Tracking of Any Point" (CVPR 2025 Highlight)
[NeurIPS 2023] Implementation of "Template-free Articulated Neural Point Clouds for Reposable View"
Official repo for "Generative Point Tracking with Flow Matching".
[ICCV 2023] Learning Fine-Grained Features for Pixel-wise Video Correspondences
Minimal code for Tapir model inference in Pytorch
[NeurIPS 2025] Efficient track anything
[NeurIPS 2023, Spotlight] Context-PIPs: Persistent Independent Particles Demands Spatial Context Features
PyTorch implementation for Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything
[ECCV'26] GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth
A partial open-source replication of D4RT: Efficiently Reconstructing Dynamic Scenes One D4RT at a Time (Google DeepMind, CVPR 2026), built using the pretrained VGGT-1B encoder and publicly available datasets.
My DATAML300 - Computer vision solutions.
Mono & stereo point-tracking for surgical endoscopy video, built for the STIR 2026 challenge (MICCAI EndoVis). Dockerized inference with MFT / LT / RLT tracker baselines.
Automatic scene normalization and coordinate contraction for multi-view 3D point tracking — MSc thesis fork of ethz-vlg/mvtracker
Count reps and measure concentric slowdown from a phone video, locally, with open-weight point tracking (LocoTrack-S).
Tracks boats in open-water video: YOLO11 detection, SAM2 masks and CoTracker3 point tracking, ~40 FPS with stable IDs.
To associate your repository with the point-tracking topic, visit your repo's landing page and select "manage topics."