qianqianwang68 / omnimotion
☆2,217Updated 10 months ago
Alternatives and similar repositories for omnimotion:
Users that are interested in omnimotion are comparing it to the libraries listed below
- Tracking Any Point (TAP)☆1,488Updated this week
- An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary alg…☆2,946Updated last year
- [ICCV 2023] Tracking Anything with Decoupled Video Segmentation☆1,373Updated last week
- Metric depth estimation from a single image☆2,581Updated last year
- SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.☆997Updated last year
- CoTracker is a model for tracking any point (pixel) on a video.☆4,286Updated 3 months ago
- [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation☆2,675Updated last month
- Segment-Anything + 3D. Let's lift anything to 3D.☆1,597Updated last year
- The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foun…☆1,751Updated last month
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything☆1,268Updated this week
- LightGlue: Local Feature Matching at Light Speed (ICCV 2023)☆3,770Updated 10 months ago
- [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model☆1,845Updated 5 months ago
- Segment Anything in High Quality [NeurIPS 2023]☆3,902Updated 4 months ago
- Segment Any RGBD☆823Updated last year
- [TPAMI'23] Unifying Flow, Stereo and Depth Estimation☆1,238Updated 4 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,604Updated 9 months ago
- Segment Anything in 3D with NeRFs (NeurIPS 2023)☆940Updated last month
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,236Updated last year
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything☆2,329Updated 4 months ago
- Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI…☆6,694Updated 11 months ago
- Particle Video Revisited☆585Updated last year
- Tracking Anything in High Quality☆749Updated last year
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,575Updated 9 months ago
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,500Updated 10 months ago
- MetaSeg: Packaged version of the Segment Anything repository☆978Updated last week
- 4DHumans: Reconstructing and Tracking Humans with Transformers☆1,358Updated 11 months ago
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆2,066Updated 2 weeks ago
- Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)☆484Updated 5 months ago
- Multiview Compressive Coding for 3D Reconstruction☆654Updated 2 years ago
- Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)☆2,880Updated last year