| title | Efficient Image Synthesis with Sphere Latent Encoder |
|---|---|
| authors | Tung Do, Thuan Hoang Nguyen, Hao Li |
| date | 2026-05-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.15592 |
| affiliation | Mohamed Bin Zayed University of Artificial Intelligence |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines. |
cite
@misc{do2026efficient,
title={Efficient Image Synthesis with Sphere Latent Encoder},
author={Tung Do and Thuan Hoang Nguyen and Hao Li},
year={2026},
eprint={2605.15592},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.15592}
}