# IDEAL：深度对齐使离散表示自编码器更优

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-09 08:00
- AIHOT 分数：57
- AIHOT 链接：https://aihot.virxact.com/items/cmqakulv20mdmslld67gvgzfo
- 原文链接：https://arxiv.org/abs/2606.11096

## AI 摘要

基于预训练视觉基础模型（VFM）的表示自编码器（RAE）在图像生成中构建语义丰富的潜空间，但重建质量受限于深层特征丢失细节。IDEAL框架通过联合对齐量化token与浅层和深层VFM特征，使离散视觉token同时保留视觉保真度和丰富语义。在ImageNet上，IDEAL达到0.61 rFID，比之前最优方法提升0.28；用于自回归图像生成时取得1.89 gFID，创下新SOTA。

## 正文

Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail. This limitation becomes even more severe after discretization, where missing low-level information is difficult to recover. In fact, we observe that shallow VFM features retain considerably richer local appearance and structural detail, which complements the high-level semantics carried by deep features used in existing RAEs. Motivated by this complementary property, we propose Ideal, an In-depth Alignment framework for discrete representation autoencoding. By jointly aligning quantized tokens with both shallow and deep VFM features, Ideal enables the resulting discrete visual tokens to preserve both visual fidelity and rich semantics. Extensive experiments demonstrate that Ideal yields superior reconstruction performance, achieving 0.61 rFID on ImageNet and outperforming the previous best method by 0.28. When used for autoregressive image generation, Ideal further produces a gFID of 1.89, establishing a new state of the art for autoregressive image generation.