Metraipolis › archive › dc_f157cb225562
Sphere Encoder 2 — arXiv:2610.02208
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02208
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T19:15:55.485Z
- SHA-256 of the archived text
54d2c88781b43efc9a6ca123d994be7f58a78bdbe7af7cba5308823df228b2c8- Stable URL of this page
https://metraipolis.com/documento/dc_f157cb225562
How to cite
Sphere Encoder 2 — arXiv:2610.02208 — arXiv (en), https://arxiv.org/abs/2610.02208 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f157cb225562 (Metraipolis archive dc_f157cb225562, sha256 54d2c88781b43efc9a6ca123d994be7f58a78bdbe7af7cba5308823df228b2c8)
BibTeX
@misc{dcf157cb225562,
title = {Sphere Encoder 2 — arXiv:2610.02208},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02208},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f157cb225562; sha256 54d2c88781b43efc9a6ca123d994be7f58a78bdbe7af7cba5308823df228b2c8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02208. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sphere Encoder is an autoencoder that generates images by decoding random points from a high-dimensional latent sphere. We identify two limitations of the original formulation that reduce its generation quality. First, random points concentrate near the equator relative to the pole on an encoded latent, but the training rotation never reaches this region, leaving a gap that limits one-step generation. Second, training for generation with pixel-wise reconstruction loss encourages the decoder to average over plausible images, producing blurry images that lack high-frequency details. We present Sphere Encoder 2 to address both limitations, substantially improving image generation quality while maintaining the speed and simplicity of a autoencoder. Models are released at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.02208 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T17:37:36.902Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).