超大模型图像自编码器，支持任意分辨率且训练更稳定。
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
- 用NaFlex实现原生分辨率泛化，适配多种长宽比。
- 50亿参数，256像素以上重建效果超越现有方法。
- 新感知损失替代传统对抗训练，支持无损扩展。
视觉变换器（ViT）自编码器已成为图像分块的有效工具，相较于卷积分块在重建质量上表现更优。然而，现有ViT分块器在非训练分辨率下性能下降，且依赖对抗损失导致难以稳定扩展。ViTok（Hansen-Estruch等，2025）发现压缩比r决定了重建与生成的权衡：低r带来更好重建但生成困难，因此提升分块器重建能力是实现更优帕累托前沿的关键。本文提出ViTok-v2，通过NaFlex实现跨分辨率与长宽比的原生支持，并引入新型DINOv3感知损失，取代LPIPS和GAN目标，确保任意规模下的稳定训练。ViTok-v2在约20亿张图像上训练，参数量达50亿，为目前最大图像自编码器。在256像素时达到或超越当前最优重建水平，在512像素及以上显著优于所有基线。与流匹配生成器联合扩展实验表明，同时扩大自编码器与生成器可推动该权衡关系的帕累托前沿上升。
原文摘要 · Abstract (English)
Vision Transformer (ViT) autoencoders have emerged as compelling tokenizers for images, offering improved reconstruction over convolutional tokenizers. However, existing ViT tokenizers cannot explore this landscape as performance degrades outside training resolutions, and reliance on adversarial losses prevents stable scaling. ViTok (Hansen-Estruch et al., 2025) found that the compression ratio r mediates a reconstruction-generation trade-off where lower r means better reconstructions but harder generations, so improving tokenizer reconstruction is key to more Pareto-optimal tokenizers. We introduce ViTok-v2, which addresses these limitations with native resolution support via NaFlex for generalization across resolutions and aspect ratios, and a novel DINOv3 perceptual loss that replaces both LPIPS and GAN objectives for stable training at any scale. ViTok-v2 is trained on about 2B images and scaled to 5B parameters, the largest image autoencoder to date. ViTok-v2 matches or exceeds state-of-the-art reconstruction at 256p and outperforms all baselines at 512p and above. In joint scaling experiments with flow matching generators, we show that scaling both the autoencoder and the generator advances the Pareto frontier of this trade-off.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。