WaiT for the Signal: Simple Frequency-Aware Flow-Matching

• URL: http://arxiv.org/abs/2607.28760v1
• Date: Thu, 30 Jul 2026 18:26:19 GMT
• Title: WaiT for the Signal: Simple Frequency-Aware Flow-Matching
• Abstract summary: We introduce WaiT, a Wavelet-aware image Transformer that decomposes generation into coarse and fine bands.<n>On ImageNet 512x512, WaiT achieves a pixel-space FID of 1.43, reducing sampling compute by up to 50%.<n>Our formulation outperforms even the strongest latent-space models on texture fidelity, and scales seamlessly to high-resolution OpenImages and to video generation.
• Score: 60.56691023057048
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flow matching treats all spatial frequencies uniformly, ignoring the natural frequency hierarchy where high-frequency bands become indistinguishable from pure noise far earlier than coarse structures. We introduce WaiT, a Wavelet-aware image Transformer that decomposes generation into coarse and fine bands via lossless wavelets. True to its name, the high-frequency bands wait for the signal: staying pure noise until coarse structure has emerged, then joining the flow for joint refinement. Since standard FID discards fine-grained detail through aggressive downsampling, we introduce a more stringent three-axis evaluation protocol to assess quality at native resolution. On ImageNet 512x512, WaiT achieves a pixel-space FID of 1.43 and is Pareto-optimal across all three axes, reducing sampling compute by up to 50%. With our largest 2B model, we set a new state-of-the-art FID of 1.3 for pixel-space models on ImageNet 512 resolution. Our formulation outperforms even the strongest latent-space models on texture fidelity, and scales seamlessly to high-resolution OpenImages and to video generation, achieving a state-of-the-art FVD of 0.84 on Kinetics-600 with no algorithmic modifications.

Related papers

• FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion [15.557373713923306]
  FrequencyBooster is a novel framework designed to empower pixel diffusion with full-frequency modeling capabilities without prohibitive overhead.<n>Our model achieves a state-of-the-art FID of textbf1.60 at $256 times 256$ resolution within only 320 epochs.<n>At $512 times 512$ resolution, FrequencyBooster attains an FID of textbf1.69, significantly outperforming existing pixel-space and latent-space generative models.
  arXiv  Detail & Related papers  (2026-05-18T02:25:07Z)
• Frequency-Aware Flow Matching for High-Quality Image Generation [40.59308529513355]
  Flow matching models have emerged as a powerful framework for realistic image generation.<n>We propose Frequency-Aware Flow Matching, which explicitly incorporates frequency-aware conditioning into the flow matching framework.<n>Our method achieves state-of-the-art performance with an FID of 1.38, surpassing the prior diffusion model DiT and flow matching model SiT by 0.79 and 0.58 FID, respectively.
  arXiv  Detail & Related papers  (2026-04-16T21:00:41Z)
• FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds [52.997038111673966]
  FLaTEC is a frequency-aware compression model that enables the compression of a full scan with high compression ratios.<n>We convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements.<n>Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78% and 94% in BD-rate on both datasets.
  arXiv  Detail & Related papers  (2025-11-25T08:37:49Z)
• 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)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation [52.56469577812338]
  We introduce StreamDiffusion, a real-time diffusion pipeline for interactive image generation.<n>Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.<n>We present a novel approach that transforms the original sequential denoising into the denoising process.
  arXiv  Detail & Related papers  (2023-12-19T18:18:33Z)
• Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging [4.15681035147785]
  In this work, we propose a novel vision transformer based tiny beamformer (Tiny-VBF) The output of our Tiny-VBF provides fast envelope detection requiring very low frame rate. We propose an accelerator architecture and implement our Tiny-VBF model on a Zynq UltraScale+ MPSoC ZCU104 FPGA.
  arXiv  Detail & Related papers  (2023-11-20T10:47:52Z)
• WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation [3.5459430566117893]
  We propose WaveGAN, a frequency-aware model for few-shot image generation. We alleviate the generator's struggles of synthesizing fine details by employing high-frequency skip connections. We achieve new state-of-the-art with FID 42.17, LPIPS 0.3868, FID 30.35, LPIPS 0.5076, and FID 4.96, LPIPS 0.3822 respectively on Flower, Animal Faces, and VGGFace.
  arXiv  Detail & Related papers  (2022-07-15T04:39:47Z)
• not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution [23.15896056344987]
  Nsb-GAN is a simple yet cost-effective two-step training framework for deep generative models. Wavelet-based down-sampling method preserves more structural information than pixel-based methods. On ImageNet 512x512, our model achieves a Fr'echet Inception Distance (FID) of 10.59 -- beating the baseline BigGAN model.
  arXiv  Detail & Related papers  (2020-09-09T17:29:40Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

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.