Improving Reconstruction of Representation Autoencoder

• URL: http://arxiv.org/abs/2602.08620v1
• Date: Mon, 09 Feb 2026 13:12:35 GMT
• Title: Improving Reconstruction of Representation Autoencoder
• Authors: Siyu Liu, Chujie Qin, Hubery Yin, Qixin Yan, Zheng-Peng Duan, Chen Li, Jing Lyu, Chun-Le Guo, Chongyi Li,
• Abstract summary: We propose LV-RAE, a representation autoencoder that augments semantic features with missing low-level information.<n>Our experiments demonstrate that LV-RAE significantly improves reconstruction fidelity while preserving the semantic abstraction.
• Score: 52.817427902597416
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are easy to learn. However, such semantic features often lack low-level information (\eg, color and texture), leading to degraded reconstruction fidelity, which has emerged as a primary bottleneck in further scaling LDMs. To address this limitation, we propose LV-RAE, a representation autoencoder that augments semantic features with missing low-level information, enabling high-fidelity reconstruction while remaining highly aligned with the semantic distribution. We further observe that the resulting high-dimensional, information-rich latent make decoders sensitive to latent perturbations, causing severe artifacts when decoding generated latent and consequently degrading generation quality. Our analysis suggests that this sensitivity primarily stems from excessive decoder responses along directions off the data manifold. Building on these insights, we propose fine-tuning the decoder to increase its robustness and smoothing the generated latent via controlled noise injection, thereby enhancing generation quality. Experiments demonstrate that LV-RAE significantly improves reconstruction fidelity while preserving the semantic abstraction and achieving strong generative quality. Our code is available at https://github.com/modyu-liu/LVRAE.

Related papers

• DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation [47.409626500688866]
  We present the DINO Spherical Autoencoder (DINO-SAE), a framework that bridges semantic representation and pixel-level reconstruction.<n>Our approach achieves state-of-the-art reconstruction quality, reaching 0.37 rFID and 26.2 dB PSNR, while maintaining strong semantic alignment to the pretrained VFM.
  arXiv  Detail & Related papers  (2026-01-30T12:25:34Z)
• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction [83.50898344094153]
  VQRAE produces Continuous semantic features for image understanding and tokens for visual generation within a unified tokenizer.<n>Design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens.<n>VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction.
  arXiv  Detail & Related papers  (2025-11-28T17:26:34Z)
• Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective [73.86108756585857]
  We analyze encoder/decoder behaviors and find that decoders depend strongly on high-frequency latent components to recover details.<n>We introduce FreqWarm, a plug-and-play frequency warm-up curriculum that increases early-stage exposure to high-frequency latent signals.
  arXiv  Detail & Related papers  (2025-11-27T09:20:36Z)
• EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model [56.53617289548353]
  EchoGen is a pioneering framework that empowers Visual Auto-Regressive ( VAR) models with subject-driven generation capabilities.<n>We employ a semantic encoder to extract the subject's abstract identity, which is injected through decoupled cross-attention to guide the overall composition.<n>To the best of our knowledge, EchoGen is the first feed-forward subject-driven framework built upon VAR models.
  arXiv  Detail & Related papers  (2025-09-30T11:45:48Z)
• Epsilon-VAE: Denoising as Visual Decoding [61.29255979767292]
  We propose denoising as decoding, shifting from single-step reconstruction to iterative refinement.<n>Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image.<n>By adopting iterative reconstruction through diffusion, our autoencoder, namely Epsilon-VAE, achieves high reconstruction quality.
  arXiv  Detail & Related papers  (2024-10-05T08:27:53Z)
• DeeDSR: Towards Real-World Image Super-Resolution via Degradation-Aware Stable Diffusion [27.52552274944687]
  We introduce a novel two-stage, degradation-aware framework that enhances the diffusion model's ability to recognize content and degradation in low-resolution images. In the first stage, we employ unsupervised contrastive learning to obtain representations of image degradations. In the second stage, we integrate a degradation-aware module into a simplified ControlNet, enabling flexible adaptation to various degradations.
  arXiv  Detail & Related papers  (2024-03-31T12:07:04Z)
• Ghost-free High Dynamic Range Imaging via Hybrid CNN-Transformer and Structure Tensor [12.167049432063132]
  We present a hybrid model consisting of a convolutional encoder and a Transformer decoder to generate ghost-free HDR images. In the encoder, a context aggregation network and non-local attention block are adopted to optimize multi-scale features. The decoder based on Swin Transformer is utilized to improve the reconstruction capability of the proposed model.
  arXiv  Detail & Related papers  (2022-12-01T15:43:32Z)

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.