IDEA-Research/RexSeek
[ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark
This tool helps you quickly find and highlight specific people or objects within images based on natural language descriptions. You provide an image and a text description, and it outputs the identified objects, even if there are multiple matches for your description. It's designed for anyone needing to precisely locate elements in visual content using descriptive text.
177 stars. No commits in the last 6 months.
Use this if you need to precisely locate multiple instances of people or objects in an image by simply describing them in everyday language.
Not ideal if you need a tool that can only detect single instances of an object or person, or if you don't require advanced natural language understanding.
Stars
177
Forks
10
Language
Python
License
—
Category
Last pushed
Oct 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/IDEA-Research/RexSeek"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video