One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation

• URL: http://arxiv.org/abs/2512.07829v2
• Date: Tue, 16 Dec 2025 18:04:34 GMT
• Title: One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
• Authors: Yuan Gao, Chen Chen, Tianrong Chen, Jiatao Gu,
• Abstract summary: Feature Auto-Encoder (FAE) adapts pre-trained visual representations into low-dimensional latents suitable for generation using as little as a single attention layer.<n>FAE achieves strong performance across class-conditional and text-to-image benchmarks.
• Score: 33.56782043207013
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual representations, either by aligning them inside VAEs or directly within the generative model. However, adapting such representations remains challenging due to fundamental mismatches between understanding-oriented features and generation-friendly latent spaces. Representation encoders benefit from high-dimensional latents that capture diverse hypotheses for masked regions, whereas generative models favor low-dimensional latents that must faithfully preserve injected noise. This discrepancy has led prior work to rely on complex objectives and architectures. In this work, we propose FAE (Feature Auto-Encoder), a simple yet effective framework that adapts pre-trained visual representations into low-dimensional latents suitable for generation using as little as a single attention layer, while retaining sufficient information for both reconstruction and understanding. The key is to couple two separate deep decoders: one trained to reconstruct the original feature space, and a second that takes the reconstructed features as input for image generation. FAE is generic; it can be instantiated with a variety of self-supervised encoders (e.g., DINO, SigLIP) and plugged into two distinct generative families: diffusion models and normalizing flows. Across class-conditional and text-to-image benchmarks, FAE achieves strong performance. For example, on ImageNet 256x256, our diffusion model with CFG attains a near state-of-the-art FID of 1.29 (800 epochs) and 1.70 (80 epochs). Without CFG, FAE reaches the state-of-the-art FID of 1.48 (800 epochs) and 2.08 (80 epochs), demonstrating both high quality and fast learning.

Related papers

• Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders [74.72147962028265]
  Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet.<n>We investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation.
  arXiv  Detail & Related papers  (2026-01-22T18:58:16Z)
• ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation [64.84095852784714]
  Residual Tokenizer (ResTok) is a 1D visual tokenizer that builds hierarchical residuals for both image tokens and latent tokens.<n>We show that restoring hierarchical residual priors in visual tokenization significantly improves AR image generation, achieving a gFID of 2.34 on ImageNet-256 with only 9 sampling steps.
  arXiv  Detail & Related papers  (2026-01-07T14:09:18Z)
• Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing [62.94394079771687]
  A burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents.<n>We propose a systematic framework to adapt understanding-oriented encoder features for generative tasks.<n>We show that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both Text-to-Image (T2I) and image editing tasks.
  arXiv  Detail & Related papers  (2025-12-19T18:59:57Z)
• Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation [52.261584726401686]
  We present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model.<n>Based on these designs, our proposed image tokenizer, VFMTok, achieves substantial improvements in image reconstruction and generation quality.
  arXiv  Detail & Related papers  (2025-07-11T09:32:45Z)
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis [15.133906625258797]
  We introduce a novel generative image modeling framework that seamlessly bridges the gap by leveraging a diffusion model to jointly model low-level image latents.<n>Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise.<n>By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance.
  arXiv  Detail & Related papers  (2025-04-22T17:41:42Z)
• D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens [80.75893450536577]
  We propose D2C, a novel two-stage method to enhance model generation capacity.<n>In the first stage, the discrete-valued tokens representing coarse-grained image features are sampled by employing a small discrete-valued generator.<n>In the second stage, the continuous-valued tokens representing fine-grained image features are learned conditioned on the discrete token sequence.
  arXiv  Detail & Related papers  (2025-03-21T13:58:49Z)
• Masked Autoencoders Are Effective Tokenizers for Diffusion Models [56.08109308294133]
  MAETok is an autoencoder that learns semantically rich latent space while maintaining reconstruction fidelity.<n>MaETok achieves significant practical improvements, enabling a gFID of 1.69 with 76x faster training and 31x higher inference throughput for 512x512 generation.
  arXiv  Detail & Related papers  (2025-02-05T18:42:04Z)
• Exploring Representation-Aligned Latent Space for Better Generation [86.45670422239317]
  We introduce ReaLS, which integrates semantic priors to improve generation performance.<n>We show that fundamental DiT and SiT trained on ReaLS can achieve a 15% improvement in FID metric.<n>The enhanced semantic latent space enables more perceptual downstream tasks, such as segmentation and depth estimation.
  arXiv  Detail & Related papers  (2025-02-01T07:42:12Z)
• Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models [33.519892081718716]
  We propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers.<n>Our proposed VA-VAE significantly expands the reconstruction-generation frontier of latent diffusion models.<n>We build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT.
  arXiv  Detail & Related papers  (2025-01-02T18:59:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.