$ε$-VAE: Denoising as Visual Decoding

• URL: http://arxiv.org/abs/2410.04081v2
• Date: Tue, 04 Feb 2025 10:54:07 GMT
• Title: $ε$-VAE: Denoising as Visual Decoding
• Authors: Long Zhao, Sanghyun Woo, Ziyu Wan, Yandong Li, Han Zhang, Boqing Gong, Hartwig Adam, Xuhui Jia, Ting Liu,
• Abstract summary: In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. We propose denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder.
• Score: 61.29255979767292
• License:
• Abstract: In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for high-quality generation. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. In this work, we offer a new perspective by proposing denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder. We evaluate our approach by assessing both reconstruction (rFID) and generation quality (FID), comparing it to state-of-the-art autoencoding approaches. By adopting iterative reconstruction through diffusion, our autoencoder, namely $\epsilon$-VAE, achieves high reconstruction quality, which in turn enhances downstream generation quality by 22% and provides 2.3$\times$ inference speedup. We hope this work offers new insights into integrating iterative generation and autoencoding for improved compression and generation.

Related papers

• Compression-Realized Deep Structural Network for Video Quality Enhancement [78.13020206633524]
  This paper focuses on the task of quality enhancement for compressed videos. Most of the existing methods lack a structured design to optimally leverage the priors within compression codecs. A new paradigm is urgently needed for a more conscious'' process of quality enhancement.
  arXiv  Detail & Related papers  (2024-05-10T09:18:17Z)
• HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression [51.04820313355164]
  HyrbidFlow combines the continuous-feature-based and codebook-based streams to achieve both high perceptual quality and high fidelity under extreme lows. Experimental results demonstrate superior performance across several datasets under extremely lows.
  arXiv  Detail & Related papers  (2024-04-20T13:19:08Z)
• Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference [95.42299246592756]
  We study the UNet encoder and empirically analyze the encoder features. We find that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps. We validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation.
  arXiv  Detail & Related papers  (2023-12-15T08:46:43Z)
• Neural Image Compression Using Masked Sparse Visual Representation [17.229601298529825]
  We study neural image compression based on the Sparse Visual Representation (SVR), where images are embedded into a discrete latent space spanned by learned visual codebooks. By sharing codebooks with the decoder, the encoder transfers codeword indices that are efficient and cross-platform robust. We propose a Masked Adaptive Codebook learning (M-AdaCode) method that applies masks to the latent feature subspace to balance and reconstruction quality.
  arXiv  Detail & Related papers  (2023-09-20T21:59:23Z)
• ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression [18.05997169440533]
  We propose ConvNeXt-ChARM, an efficient ConvNeXt-based transform coding framework, paired with a compute-efficient channel-wise auto-regressive auto-regressive. We show that ConvNeXt-ChARM brings consistent and significant BD-rate (PSNR) reductions estimated on average to 5.24% and 1.22% over the versatile video coding (VVC) reference encoder (VTM-18.0) and the state-of-the-art learned image compression method SwinT-ChARM.
  arXiv  Detail & Related papers  (2023-07-12T11:45:54Z)
• GAN-Based Multi-View Video Coding with Spatio-Temporal EPI Reconstruction [19.919826392704472]
  We propose a novel multi-view video coding method that leverages the image generation capabilities of Generative Adrial Network (GAN) At the encoder, we construct atemporal Epipolar Plane Image (EPI) decoder and further utilize a convolutional network to extract the latent code of a GAN as Side Information (SI) At the side, we combine SI and adjacent viewpoints to reconstruct intermediate views using the GAN generator.
  arXiv  Detail & Related papers  (2022-05-07T08:52:54Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding [59.48857453699463]
  In sequence-to-sequence learning, the decoder relies on the attention mechanism to efficiently extract information from the encoder. Recent work has proposed to use representations from different encoder layers for diversified levels of information. We propose layer-wise multi-view decoding, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder layers are supplemented for a stereoscopic view of the source sequences.
  arXiv  Detail & Related papers  (2020-05-16T20:00:39Z)

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.