hkchengrex/CascadePSP
[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
This tool refines the edges of object masks in very high-resolution images. You provide an image and an initial, rough mask highlighting an object, and it produces a much cleaner, more precise mask. It's designed for professionals in fields like image editing, scientific imaging, or computer vision research who need pixel-perfect object outlines.
878 stars.
Use this if you need to accurately segment objects from their backgrounds in high-detail images, where initial masks might be coarse or jagged.
Not ideal if you need to generate initial object masks from scratch or if you primarily work with low-resolution images where fine detail isn't critical.
Stars
878
Forks
97
Language
Python
License
MIT
Category
Last pushed
Jan 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hkchengrex/CascadePSP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
nv-tlabs/GSCNN
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
lim-anggun/FgSegNet
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural...
jiwoon-ahn/irn
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
suyukun666/UFO
Official PyTorch implementation of the “A Unified Transformer Framework for Co-Segmentation,...
Chrisding/seal
Code for Simultaneous Edge Alignment and Learning (SEAL)