Method · Optimization in a generative latent space
GSDD
GSDD: Generative Space Dataset Distillation for Image Super-resolution
Haiyu Zhang, Shaolin Su, Yu Zhu, Jinqiu Sun, Yanning Zhang
AAAI 2024 · first public 2024-01
In one paragraph
GSDD distills a low-resolution/high-resolution image-pair dataset for super-resolution by optimizing codes in the latent space of a pretrained GAN via GAN-inversion, rather than selecting or synthesizing pixels directly, so the stored artifact is a small set of latent codes plus the frozen generator. The paper reports super-resolution performance comparable to prior state-of-the-art distillation methods with about an 8x increase in training efficiency and roughly 93.2% less storage, and shows generalization to real-world degraded images.
Where it sits
- Optimization in a generative latent space (Generative priors)
- Setting: Detection, segmentation and low-level vision
Design choices
| Prior / networks used | gan |
BibTeX (generated; prefer the venue's official entry)
@article{zhang2024gsdd,
title = {GSDD: Generative Space Dataset Distillation for Image Super-resolution},
author = {Haiyu Zhang and Shaolin Su and Yu Zhu and Jinqiu Sun and Yanning Zhang},
journal = {AAAI 2024},
year = {2024}
}Nearby in Optimization in a generative latent space
Condensing Action Segmentation Datasets via Generative Network Inversion
Guodong Ding, Rongyu Chen, Angela Yao · CVPR 2025notableVideopaper ↗