CrossFlow: One-Step Generation Across Latent and Pixel Spaces

• URL: http://arxiv.org/abs/2606.19970v1
• Date: Thu, 18 Jun 2026 09:10:28 GMT
• Title: CrossFlow: One-Step Generation Across Latent and Pixel Spaces
• Abstract summary: CrossFlow is a cross-space flow formulation that maps noisy latent inputs directly to pixel-space images.<n>On class-conditional ImageNet-1k at $256times256$, CrossFlow-XL achieves 1.62 FID with one function evaluation.
• Score: 61.08358796319721
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most diffusion and flow-matching generators define the prior, probability path, and prediction target in the same representation space. Latent diffusion improves efficiency by moving this path into an autoencoder latent space, but the final sample is still produced by a separately trained decoder. This separation creates a mismatch: the generator is optimized for latent-space prediction, while final quality depends on how the decoder handles generated latents that may differ from clean encoder outputs. We introduce CrossFlow, a cross-space flow formulation that maps noisy latent inputs directly to pixel-space images. The key technical step is a velocity-free one-step objective: the latent trajectory defines the training path, but the supervised prediction is an image rather than a latent displacement. This lets one model act both as a one-step latent-to-pixel generator and as a decoder replacement for latent diffusion pipelines. On class-conditional ImageNet-1k at $256\times256$, CrossFlow-XL achieves 1.62 FID with one function evaluation. Ablations show that the latent encoder and pixel-space perceptual and adversarial losses are important for fidelity. These results indicate that cross-space flow objectives can combine the efficiency of latent representations with direct pixel-space supervision, without requiring a separate decoder at inference.

Related papers

• Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion [46.51681899437508]
  We introduce Spectral Forcing, a parameter-free, time-conditional 2D-DCT low-pass operator applied to the noisy input before the patch embedder.<n>Its cutoff expands monotonically with the diffusion time and becomes the identity at the data endpoint.<n>On ImageNet-256 with JiT-700M/32, Spectral Forcing consistently improves both FID and Inception Score across different training epochs.
  arXiv  Detail & Related papers  (2026-06-13T10:29:11Z)
• End-to-End Training for Unified Tokenization and Latent Denoising [82.91537591286554]
  We propose UNITE - an autoencoder architecture for unified tokenization and latent diffusion.<n>UNITE consists of a Generative that serves as both image tokenizer and latent generator via weight sharing.<n>We show that single stage joint training of tokenization & generation from scratch is feasible.
  arXiv  Detail & Related papers  (2026-03-23T17:59:49Z)
• Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation [9.199518837644424]
  Diffusion-based decoders have been adopted in image tokenization to reconstruct images from latent representations with high fidelity.<n>We introduce a two-stage acceleration framework to address this inefficiency.<n>We distill the diffusion decoder at each scale into a single-step denoising model, enabling fast and high-quality reconstructions.
  arXiv  Detail & Related papers  (2026-03-20T02:24:58Z)
• Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation [36.41177812868683]
  Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling.<n>We propose Latent Forcing, a simple modification to existing architectures that achieves the efficiency of latent diffusion while operating on raw natural images.<n>Latent Forcing achieves a new state-of-the-art for diffusion transformer-based pixel generation at our compute scale.
  arXiv  Detail & Related papers  (2026-02-11T22:09:58Z)
• One-step Latent-free Image Generation with Pixel Mean Flows [22.294629970410508]
  We propose "pixel MeanFlow" (pMF) to formulate the network output space and the loss space separately.<n>pMF achieves strong results for one-step latent-free generation on ImageNet at 256x256 resolution (2.22 FID) and 512x512 resolution (2.48 FID)
  arXiv  Detail & Related papers  (2026-01-29T18:59:56Z)
• DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation [93.6273078684831]
  We propose a frequency-DeCoupled pixel diffusion framework to pursue a more efficient pixel diffusion paradigm.<n>With the intuition to decouple the generation of high and low frequency components, we leverage a lightweight pixel decoder to generate high-frequency details conditioned on semantic guidance.<n>Experiments show that DeCo achieves superior performance among pixel diffusion models, attaining FID of 1.62 (256x256) and 2.22 (512x512) on ImageNet.
  arXiv  Detail & Related papers  (2025-11-24T17:59:06Z)
• Restoring Images in Adverse Weather Conditions via Histogram Transformer [75.74328579778049]
  We propose an efficient Histogram Transformer (Histoformer) for restoring images affected by adverse weather. It is powered by a mechanism dubbed histogram self-attention, which sorts and segments spatial features into intensity-based bins. To boost histogram self-attention, we present a dynamic-range convolution enabling conventional convolution to conduct operation over similar pixels.
  arXiv  Detail & Related papers  (2024-07-14T11:59:22Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• TFill: Image Completion via a Transformer-Based Architecture [69.62228639870114]
  We propose treating image completion as a directionless sequence-to-sequence prediction task. We employ a restrictive CNN with small and non-overlapping RF for token representation. In a second phase, to improve appearance consistency between visible and generated regions, a novel attention-aware layer (AAL) is introduced.
  arXiv  Detail & Related papers  (2021-04-02T01:42:01Z)

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.