sam-hq
sam-pt
sam-hq | sam-pt | |
---|---|---|
6 | 1 | |
3,401 | 905 | |
4.8% | 3.2% | |
8.2 | 5.7 | |
5 months ago | 4 months ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sam-hq
-
12-Jun-2023
Segment Anything in High Quality (https://arxiv.org/abs/2306.01567)
-
Segment Anything in High Quality
GitHub: https://github.com/SysCV/SAM-HQ
- GitHub - SysCV/sam-hq: Segment Anything in High Quality
-
This Week in AI (6/5/23): “Risk of Extinction,” Nvidia’s 3D magic, and the Air Force’s AI drone drama.
Paper here, Github repo here.
sam-pt
-
using AI to fill the scenes vertically
Part of this process can be a remastering step also for old videos. Masking backgrounds across frames and performing super-resolution with all known references and scaling details for characters using fine-tuned models for each actor. We have a lot new SAM tools to assist with this process. It probably won't be magically done for a while, but a few people could remaster a show rather than a large team.
What are some alternatives?
segment-geospatial - A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
Semantic-SAM - Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
SegmentAnythingin3D - Segment Anything in 3D with NeRFs (NeurIPS 2023)
Segment-and-Track-Anything - An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
bloop - bloop is a fast code search engine written in Rust.
SlicerTomoSAM - An extension of 3D Slicer using the Segment Anything Model (SAM) to aid the segmentation of 3D data from tomography or other imaging techniques.
InternGPT - InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)