Awesome
Optimize and Reduce: A Top-Down Approach for Image Vectorization
π News
2023-12
Our paper: Optimize and Reduce: A Top-Down Approach for Image Vectorization was accepted byAAAI 2024
We propose Optimize & Reduce (O&R), a top-down approach to vectorization that is both fast and domain-agnostic. O&R aims to attain a compact representation of input images by iteratively optimizing BΓ©zier curve parameters and significantly reducing the number of shapes, using a devised importance measure.
By Or Hirschorn*, Amir Jevnisek*, and Shai Avidan
Where * denotes equal contribution.
π Setup
cd docker
docker build -t optimize_and_reduce_aaai .
cd ..
docker run -v $(pwd):/home/code -it optimize_and_reduce_aaai /bin/bash
π Run
- Running O&R:
python reduce_or_add_and_optimize.py --target target_images/083.png \
--scheduler 256 128 64 --num_iter 100 100 100 \
--recons_loss_type l1_and_clip_mix --l1_and_clip_alpha 0.95 \
--geometric_loss_type geometric --ranking_loss_type mse \
--canvas_width 256 --canvas_height 256 --advanced_logging
- Running the baseline DiffVG:
python basic_diffvg.py --target target_images/083.png \
--num_paths 64 --num_epochs 1 --num_iter 400 \
--recons_loss_type l1 --geometric_loss_type none \
--canvas_width 256 --canvas_height 256 --scheduler 400 \
--init_type random
π Dataset Download
- Old Emojis, take the images from this list
- New Emojis, take the images from this list
- Free-SVG
- NFT-Apes
- Midjourney Images
π Cite:
Please consider citing this paper if you found the code
or data
useful.
@inproceedings{DBLP:conf/aaai/OptimizeReduce,
author = {Or Hirchorn and
Amir Jevnisek and
Shai Avidan},
title = {Optimize and Reduce: A Top-Down Approach for Image Vectorization},
booktitle = {{AAAI}},
publisher = {{AAAI} Press},
year = {2024}
}