MaticFuc/ECCV_TransFusion
Official implementation of the ECCV 2024 paper: TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection
This helps quality control and inspection professionals automatically find defects on product surfaces. It takes images of products, either 2D or 3D, and identifies unusual areas, outputting precise locations of anomalies. This is ideal for manufacturing and industrial settings to ensure product quality without manual inspection.
No commits in the last 6 months.
Use this if you need to reliably detect surface anomalies in images of products, such as in automated manufacturing inspection lines.
Not ideal if you are looking for a general-purpose object detection system or if your anomalies don't involve distinct surface variations.
Stars
47
Forks
3
Language
Python
License
MIT
Category
Last pushed
Apr 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MaticFuc/ECCV_TransFusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aleflabo/MoCoDAD
The official PyTorch implementation of the IEEE/CVF International Conference on Computer Vision...
caiyu6666/DDAD
[MICCAI 2022] Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rays
FinnBehrendt/patched-Diffusion-Models-UAD
Codebase for Patched Diffusion Models for Unsupervised Anomaly Detection .
FinnBehrendt/Conditioned-Diffusion-Models-UAD
Codebase for Conditioned Diffusion Models for Unsupervised Anomaly Detection
caiyu6666/DDAD-ASR
[MedIA 2023] Dual-distribution discrepancy with self-supervised refinement for anomaly detection...