Gorilla-Lab-SCUT/PaDT
[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs"
This project helps visual content analysts and researchers accurately identify and segment objects within images based on text descriptions. You input an image and a natural language query about an object, and it outputs the exact location (bounding box) or pixel-level segmentation mask for that object, along with relevant textual responses. This is ideal for those who need precise visual grounding from text prompts across various image understanding tasks.
251 stars.
Use this if you need a multimodal AI model that can precisely identify and segment specific objects in images based on descriptive text queries, directly generating visual outputs rather than just coordinate numbers.
Not ideal if your primary need is general image captioning or if you don't require highly precise visual localization and segmentation tied to textual references.
Stars
251
Forks
13
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Gorilla-Lab-SCUT/PaDT"
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