k8xu/amodal
Official code for "Amodal Completion via Progressive Mixed Context Diffusion" [CVPR 2024 Highlight]
This project helps computer vision researchers and developers restore the complete appearance of objects in images, even when parts are hidden or cut off. You input an image with an occluded object, and it outputs the original image with the missing parts of the object filled in, as if the obstruction was removed. It's designed for those working with image analysis, reconstruction, or scene understanding.
No commits in the last 6 months.
Use this if you need to accurately reconstruct the full form of objects in images that are partially hidden by other objects or cut off by the image boundary, without needing extensive custom model training.
Not ideal if you're looking for a simple, out-of-the-box application for everyday photo editing, as it requires some technical setup.
Stars
55
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/k8xu/amodal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators