https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once

Last synced: 5 days ago
JSON representation

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

• Host: GitHub
• URL: https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once
• Owner: UX-Decoder
• License: apache-2.0
• Created: 2023-04-12T05:08:43.000Z (over 1 year ago)
• Default Branch: v1.0
• Last Pushed: 2024-08-19T08:01:54.000Z (3 months ago)
• Last Synced: 2024-10-29T15:03:17.560Z (10 days ago)
• Language: Python
• Homepage:
• Size: 297 MB
• Stars: 4,364
• Watchers: 59
• Forks: 397
• Open Issues: 50
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-vision-language-pretraining - SEEM
• awesome-segment-anything-extensions - Repo
• AiTreasureBox - UX-Decoder/Segment-Everything-Everywhere-All-At-Once - 11-02_4367_0](https://img.shields.io/github/stars/UX-Decoder/Segment-Everything-Everywhere-All-At-Once.svg) |Official implementation of the paper "Segment Everything Everywhere All at Once"| (Repos)
• awesome-llm-and-aigc - SEEM - Decoder/Segment-Everything-Everywhere-All-At-Once?style=social"/> : We introduce SEEM that can Segment Everything Everywhere with Multi-modal prompts all at once. SEEM allows users to easily segment an image using prompts of different types including visual prompts (points, marks, boxes, scribbles and image segments) and language prompts (text and audio), etc. It can also work with any combinations of prompts or generalize to custom prompts! "Segment Everything Everywhere All at Once". (**[arXiv 2023](https://arxiv.org/abs/2304.06718)**). (Summary)
• awesome-llm-and-aigc - SEEM - Decoder/Segment-Everything-Everywhere-All-At-Once?style=social"/> : We introduce SEEM that can Segment Everything Everywhere with Multi-modal prompts all at once. SEEM allows users to easily segment an image using prompts of different types including visual prompts (points, marks, boxes, scribbles and image segments) and language prompts (text and audio), etc. It can also work with any combinations of prompts or generalize to custom prompts! "Segment Everything Everywhere All at Once". (**[arXiv 2023](https://arxiv.org/abs/2304.06718)**). (Summary)