Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chang, Hun, Cha, Byunghee, Ye, Jong Chul
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.22904
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917476251467776
author Chang, Hun
Cha, Byunghee
Ye, Jong Chul
author_facet Chang, Hun
Cha, Byunghee
Ye, Jong Chul
contents Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generative performance. Unfortunately, existing approaches often suffer from limited reconstruction fidelity due to the loss of high-frequency details. In this work, we present the \textbf{\em Hyperspherical Autoencoder (HAE)}, a framework that bridges semantic representation and pixel-level reconstruction. Our key insight is that while semantic information in contrastive representations is primarily directional, enforcing strict magnitude matching hinders the preservation of fine-grained details. To address this, we introduce a {\em Directional Feature Alignment} objective that enforces semantic consistency while allowing flexible feature magnitudes for detail retention, alongside a {\em Hierarchical Convolutional Patch Embedding} module to enhance local structure preservation. Furthermore, observing that SSL-based representations intrinsically lie on a hypersphere, we employ {\em Riemannian Flow Matching} to train a Diffusion Transformer (DiT) directly on this spherical latent manifold. Notably, our manifold-aware DiT exhibits highly efficient convergence, achieving an exceptional gFID of \textbf{1.96} alongside a reconstruction rFID of \textbf{0.78} and a PSNR of \textbf{25.2} dB, validating the advantages of our manifold-aware approach.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22904
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation
Chang, Hun
Cha, Byunghee
Ye, Jong Chul
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generative performance. Unfortunately, existing approaches often suffer from limited reconstruction fidelity due to the loss of high-frequency details. In this work, we present the \textbf{\em Hyperspherical Autoencoder (HAE)}, a framework that bridges semantic representation and pixel-level reconstruction. Our key insight is that while semantic information in contrastive representations is primarily directional, enforcing strict magnitude matching hinders the preservation of fine-grained details. To address this, we introduce a {\em Directional Feature Alignment} objective that enforces semantic consistency while allowing flexible feature magnitudes for detail retention, alongside a {\em Hierarchical Convolutional Patch Embedding} module to enhance local structure preservation. Furthermore, observing that SSL-based representations intrinsically lie on a hypersphere, we employ {\em Riemannian Flow Matching} to train a Diffusion Transformer (DiT) directly on this spherical latent manifold. Notably, our manifold-aware DiT exhibits highly efficient convergence, achieving an exceptional gFID of \textbf{1.96} alongside a reconstruction rFID of \textbf{0.78} and a PSNR of \textbf{25.2} dB, validating the advantages of our manifold-aware approach.
title Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.22904