eliahuhorwitz/DeepSIM
Official PyTorch implementation of the paper: "DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample" (ICCV 2021 Oral)
This tool helps graphic designers, marketers, and researchers manipulate specific shapes within an image using a single training example. You provide one real image and a simple corresponding outline (like an edge map or segmentation). Then, you can modify that outline, and the tool generates a new image reflecting those changes, like altering facial features or car shapes.
425 stars. No commits in the last 6 months.
Use this if you need to precisely edit the shape of objects in an image without needing a large dataset, and you can provide a simple primitive representation of the target object.
Not ideal if you need to generate entirely new objects, change image style, or perform complex edits that go beyond manipulating existing shapes.
Stars
425
Forks
49
Language
Python
License
—
Category
Last pushed
Nov 22, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/eliahuhorwitz/DeepSIM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zhangyi-3/IDR
Self-Supervised Image Denoising via Iterative Data Refinement (CVPR2022)
yinboc/liif
Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)
XingangPan/deep-generative-prior
Code for deep generative prior (ECCV2020 oral)
mv-lab/swin2sr
[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. ...
cszn/FFDNet
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising (TIP, 2018)