Mukosame/AODA
Official implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)
This tool helps graphic designers, artists, or researchers create realistic photographs from freehand sketches, even if the specific object in the sketch wasn't part of the training data. You provide a rough drawing and its category label, and the tool generates a high-quality photo with appropriate colors and textures. It's ideal for visual content creators exploring new designs or anyone needing to transform conceptual sketches into photorealistic images.
No commits in the last 6 months.
Use this if you need to transform simple, freehand sketches into detailed, realistic photographs, especially for subjects not explicitly seen during the tool's initial learning phase.
Not ideal if you need to generate sketches from photos, or if you require pixel-perfect reproduction of complex scenes rather than generating realistic representations of individual objects.
Stars
85
Forks
11
Language
Python
License
BSD-3-Clause
Category
Last pushed
Dec 26, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Mukosame/AODA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
WinfredGe/T2S
[IJCAI 2025] Official implementation of "T2S: High-resolution Time Series Generation with...
monniert/dti-sprites
(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper
shashankvkt/AlignMixup_CVPR22
Official Implementation of AlignMixup - CVPR 2022
JinXins/Adversarial-AutoMixup
Official PyTorch(MMCV) implementation of “Adversarial AutoMixup” (ICLR 2024 spotlight)
ValentinKoch/SVDNA
The github repository of the paper "Noise Transfer for Unsupervised Domain Adaptation of Retinal...