facebookresearch / co-tracker
CoTracker is a model for tracking any point (pixel) on a video.
☆4,136Updated 3 weeks ago
Alternatives and similar repositories for co-tracker:
Users that are interested in co-tracker are comparing it to the libraries listed below
- [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation☆7,291Updated 7 months ago
- ☆2,182Updated 8 months ago
- Tracking Any Point (TAP)☆1,394Updated 2 months ago
- [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model☆1,809Updated 3 months ago
- Segment Anything in High Quality [NeurIPS 2023]☆3,805Updated 2 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆14,142Updated last month
- [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation☆2,553Updated 2 months ago
- Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything☆1,203Updated 3 months ago
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,494Updated 6 months ago
- Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI…☆6,615Updated 8 months ago
- PyTorch code and models for the DINOv2 self-supervised learning method.☆9,827Updated 6 months ago
- Efficient vision foundation models for high-resolution generation and perception.☆2,641Updated 3 weeks ago
- An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary alg…☆2,883Updated 9 months ago
- Metric depth estimation from a single image☆2,473Updated 9 months ago
- LightGlue: Local Feature Matching at Light Speed (ICCV 2023)☆3,600Updated 8 months ago
- High-resolution models for human tasks.☆4,831Updated 3 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,478Updated 7 months ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,324Updated 6 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆7,427Updated 6 months ago
- [ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy☆2,393Updated 4 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆1,671Updated 2 months ago
- Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"☆6,512Updated this week
- Fast Segment Anything☆7,704Updated 6 months ago
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,454Updated 7 months ago
- DUSt3R: Geometric 3D Vision Made Easy☆5,829Updated 5 months ago
- [CVPR 2024] Real-Time Open-Vocabulary Object Detection☆5,057Updated 3 months ago
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything☆2,264Updated last month
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆985Updated last year
- [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation☆4,614Updated 3 weeks ago
- [SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research☆1,056Updated last month