DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression

• URL: http://arxiv.org/abs/2603.13162v1
• Date: Fri, 13 Mar 2026 16:56:00 GMT
• Title: DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
• Abstract summary: DiT-IC is an Aligned Diffusion Transformer for Image Compression.<n>It replaces the U-Net with a Diffusion Transformer capable of performing diffusion in latent space entirely at 32x downscaled resolution.<n>It can reconstruct 2048x2048 images on a 16 GB laptop GPU.
• Score: 56.68267606568949
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where hierarchical downsampling forces diffusion to operate in shallow latent spaces (typically with only 8x spatial downscaling), resulting in excessive computation. In contrast, conventional VAE-based codecs work in much deeper latent domains (16x - 64x downscaled), motivating a key question: Can diffusion operate effectively in such compact latent spaces without compromising reconstruction quality? To address this, we introduce DiT-IC, an Aligned Diffusion Transformer for Image Compression, which replaces the U-Net with a Diffusion Transformer capable of performing diffusion in latent space entirely at 32x downscaled resolution. DiT-IC adapts a pretrained text-to-image multi-step DiT into a single-step reconstruction model through three key alignment mechanisms: (1) a variance-guided reconstruction flow that adapts denoising strength to latent uncertainty for efficient reconstruction; (2) a self-distillation alignment that enforces consistency with encoder-defined latent geometry to enable one-step diffusion; and (3) a latent-conditioned guidance that replaces text prompts with semantically aligned latent conditions, enabling text-free inference. With these designs, DiT-IC achieves state-of-the-art perceptual quality while offering up to 30x faster decoding and drastically lower memory usage than existing diffusion-based codecs. Remarkably, it can reconstruct 2048x2048 images on a 16 GB laptop GPU.

Related papers

• Efficient Learned Image Compression without Entropy Coding [62.01837001379442]
  We present Entropy-Coding Free Learned Image Compression (EF-LIC)<n>EF-LIC is a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency.<n>Experiments show EF-LIC achieves up to 67.86% reduction over MS-ILLM on Kodak with LPIPS.
  arXiv  Detail & Related papers  (2026-05-22T07:37:30Z)
• Laminating Representation Autoencoders for Efficient Diffusion [18.989001805139573]
  Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents.<n>We introduce FlatDINO, a variational autoencoder that compresses this representation into a one-dimensional sequence of just 32 continuous tokens.
  arXiv  Detail & Related papers  (2026-02-04T18:57:33Z)
• Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder [41.0853762937392]
  We propose a novel Asymmetric Extreme Image Compression (AEIC) framework that pursues simultaneously encoding simplicity and decoding quality.<n>AEIC employs moderate or even shallow encoder networks, while leveraging an one-step diffusion decoder to maintain high-fidelity and high-realism.<n>Experiments demonstrate that AEIC not only outperforms existing methods on rate-distortion-perception performance at ultra-lows, but also delivers exceptional encoding efficiency for 35.8 FPS on 1080P input images.
  arXiv  Detail & Related papers  (2025-12-13T07:59:48Z)
• Diffusion Transformers with Representation Autoencoders [35.43400861279246]
  Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT)<n>Most DiTs continue to rely on the original VAE encoder, which introduces several limitations.<n>In this work, we explore replacing the VAE with pretrained representation encoders paired with trained decoders, forming what we term Representation Autoencoders (RAE)
  arXiv  Detail & Related papers  (2025-10-13T17:51:39Z)
• StableCodec: Taming One-Step Diffusion for Extreme Image Compression [19.69733852050049]
  Diffusion-based image compression has shown remarkable potential for achieving ultra-low coding (less than 0.05 bits per pixel) with high realism.<n>Current approaches require a large number of denoising steps at the decoder to generate realistic results under extreme constraints.<n>We introduce StableCodec, which enables one-step diffusion for high-fidelity and high-realism extreme image compression.
  arXiv  Detail & Related papers  (2025-06-27T07:39:21Z)
• Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion [28.61304513668606]
  ResULIC is a residual-guided ultra lowrate image compression system.<n>It incorporates residual signals into both semantic retrieval and the diffusion-based generation process.<n>It achieves superior objective and subjective performance compared to state-of-the-art diffusion-based methods.
  arXiv  Detail & Related papers  (2025-05-13T06:51:23Z)
• DDT: Decoupled Diffusion Transformer [51.84206763079382]
  Diffusion transformers encode noisy inputs to extract semantic component and decode higher frequency with identical modules.<n>textbfcolorddtDecoupled textbfcolorddtTransformer(textbfcolorddtDDT)<n>textbfcolorddtTransformer(textbfcolorddtDDT)<n>textbfcolorddtTransformer(textbfcolorddtDDT)
  arXiv  Detail & Related papers  (2025-04-08T07:17:45Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  New tokenizer, Diffusion Conditioned-based Gene Tokenizer, replaces GAN-based decoder with conditional diffusion model.<n>We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch.<n>Even a scaled-down version of CDT (3$times inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)
• Modeling Lost Information in Lossy Image Compression [72.69327382643549]
  Lossy image compression is one of the most commonly used operators for digital images. We propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem.
  arXiv  Detail & Related papers  (2020-06-22T04:04:56Z)

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.