Yuki-11/CSBSR
Official PyTorch implementation of the paper "Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images", IEEE Transactions on Instrumentation and Measurement (TIM) 2024. CSBSR is an advanced version of our previous work CSSR [MVA'21].
This project helps civil engineers, inspectors, and maintenance teams accurately identify cracks in infrastructure from degraded images. It takes blurry, low-resolution images of surfaces as input and outputs a much clearer, high-resolution image with precise crack locations highlighted, even when the original blur source is unknown. This allows for better assessment of structural integrity.
No commits in the last 6 months.
Use this if you need to reliably detect and segment cracks from images that are blurry or low quality, without needing to know why they are degraded.
Not ideal if your primary goal is general image enhancement without a specific focus on crack detection, or if you only work with perfectly clear, high-resolution images.
Stars
45
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
May 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Yuki-11/CSBSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Tengfei-Wang/DCSR
[ICCV 2021 (Oral Presentation)] Dual-Camera Super-Resolution with Aligned Attention Modules (RefSR)
msmsajjadi/FRVSR
Frame-Recurrent Video Super-Resolution (official repository)
WWIIITT/360-degree-video-super-resolution
Leveraging AI, this solution boosts 360° video quality through 4x upscaling with Real-ESRGAN. It...
xuxy09/RawSR
Exploiting raw images for real-scene super-resolution, TPAMI 2021
o-messai/DDSRNet
DDSRNet (A Deep Model for Denoising and Super-Resolution) is a new two-stage learning...