facebookresearch / co-tracker
CoTracker is a model for tracking any point (pixel) on a video.
☆2,674Updated last month
Related projects: ⓘ
- ☆2,111Updated 3 months ago
- Segment Anything in High Quality [NeurIPS 2023]☆3,643Updated 2 months ago
- Tracking Any Point (TAP)☆1,264Updated this week
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,309Updated last month
- [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation☆6,769Updated 2 months ago
- [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation☆2,199Updated 3 weeks ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆6,262Updated last month
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆953Updated 7 months ago
- Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI…☆6,407Updated 3 months ago
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,217Updated last month
- An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary alg…☆2,770Updated 4 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,255Updated 2 months ago
- Open-source and strong foundation image recognition models.☆2,745Updated last month
- [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model☆1,722Updated 6 months ago
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything☆2,081Updated 3 months ago
- Metric depth estimation from a single image☆2,247Updated 4 months ago
- PyTorch code and models for the DINOv2 self-supervised learning method.☆8,791Updated last month
- Segment-Anything + 3D. Let's lift anything to 3D.☆1,538Updated last year
- Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with dive…☆1,662Updated last year
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,104Updated last year
- LightGlue: Local Feature Matching at Light Speed (ICCV 2023)☆3,300Updated 2 months ago
- This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!☆4,681Updated 7 months ago
- Fast Segment Anything☆7,349Updated last month
- [CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution☆1,546Updated 3 months ago
- Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)☆4,330Updated 5 months ago
- SAM with text prompt☆1,542Updated last month
- Tracking Anything in High Quality☆743Updated 9 months ago
- Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)☆2,650Updated 9 months ago
- Painter & SegGPT Series: Vision Foundation Models from BAAI☆2,497Updated 10 months ago
- MetaSeg: Packaged version of the Segment Anything repository☆945Updated this week