Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

• URL: http://arxiv.org/abs/2606.15236v2
• Date: Tue, 16 Jun 2026 13:59:42 GMT
• Title: Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
• Abstract summary: 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.
• Score: 46.51681899437508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pixel-space diffusion models are trained on full-bandwidth noisy images, yet the useful signal available to the denoiser is strongly frequency dependent. Under rectified-flow diffusion and natural-image power-law spectra, the per-band data-to-noise contour $k^{*}(t) = (1-t)^{-2/α}$ separates a signal-bearing low-frequency region from a noise-dominated high-frequency region at each time $t$. We show that this implicit coarse-to-fine structure is not merely descriptive: it induces a capacity-allocation problem. A standard pixel-space denoiser must discover the moving bandwidth boundary internally and can spend computation on frequency-time regions where the optimal prediction collapses to deterministic baselines rather than data-distribution modeling. To make this boundary explicit, we introduce Spectral Forcing, a parameter-free, time-conditional 2D-DCT low-pass operator applied to the noisy input before the patch embedder. Its cutoff expands monotonically with the diffusion time and becomes the identity at the data endpoint. Through controlled synthetic experiments, we identify the regime in which the operator is beneficial: coarse patch tokenization and data whose high-frequency content is predominantly noise rather than essential signal. On ImageNet-256 with JiT-700M/32, Spectral Forcing consistently improves both FID and Inception Score across different training epochs, demonstrating robust gains throughout training; at finer tokenization, the spectral forcing is still competitive. We further insert the unchanged operator into SenseNova-U1, a unified text-to-image model, where it improves DPG-Bench and GenEval, showing that the input-side spectral prior transfers beyond class-conditional generation. These results suggest a route to capacity-efficient pixel-space diffusion by showing the signal and hiding the noise.

Related papers

• Fractional-Order Adaptive Motion Magnification: Phase-Reliability Weighting for Noise-Constrained Video Amplification [51.56484100374058]
  We propose Fractional-order Adaptive Motion Magnification, a pipeline developed first offline and then as a causal stream.<n>It replaces the constant temporal gain with a Grnwald--Letnikov derivative of fractional order, giving continuous control over high-frequency emphasis.<n>Real videos show improved spatial selectivity and lower background noise in every case.
  arXiv  Detail & Related papers  (2026-09-03T21:43:22Z)
• Balancing Frequencies and Pixels in Flow Matching [43.75072807799361]
  Pixel-space reconstruction objectives treat all spatial errors uniformly, causing low frequencies to dominate the optimization signal.<n>We propose a Focal Log-Frequency Loss objective that equalizes the learning signal across frequencies.<n>Our approach is conceptually simple, requires no architectural changes, and acts as a drop-in replacement for flow matching losses.
  arXiv  Detail & Related papers  (2026-09-02T15:49:24Z)
• Drift-Aware RL-based Wavelet Denoising for Network-Traffic Anomaly Detection [1.5469452301122173]
  Traffic-utilisation measurements for network monitoring are corrupted by additive noise and statistical drift.<n>We propose a drift-aware framework treating adaptive wavelet denoising as a preprocessing layer optimised for two tasks.
  arXiv  Detail & Related papers  (2026-07-22T10:52:05Z)
• CrossFlow: One-Step Generation Across Latent and Pixel Spaces [61.08358796319721]
  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.
  arXiv  Detail & Related papers  (2026-06-18T09:10:28Z)
• ZoomSpec: A Physics-Guided Coarse-to-Fine Framework for Wideband Spectrum Sensing [7.560433707709695]
  ZoomSpec is a physics-guided coarse-to-fine framework integrating signal processing priors with deep learning.<n> Evaluations on the SpaceNet real-world dataset demonstrate state-of-the-art 78.1 mAP@0.5:0.95.
  arXiv  Detail & Related papers  (2026-04-15T07:29:25Z)
• Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations [7.7579389797716365]
  We propose an adaptive local frequency filtering method for Fourier-encoded INRs.<n>The proposed method introduces a spatially varying parameter $(mathbfx)$ to modulate encoded Fourier components.<n>Experiments on 2D image fitting, 3D shape representation, and sparse data reconstruction demonstrate that the proposed method consistently improves reconstruction quality.
  arXiv  Detail & Related papers  (2026-04-03T08:04:30Z)
• 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)
• Improving Accuracy and Efficiency of Implicit Neural Representations: Making SIREN a WINNER [0.0]
  We identify and address a fundamental limitation of sinusoidal representation networks (SIRENs)<n>In extreme cases, when the network's frequency support misaligns with the target spectrum, a'spectral bottleneck' is observed.<n>We propose WINNER - Weight Initialization with Noise for Neural Representations.
  arXiv  Detail & Related papers  (2025-09-16T11:41:13Z)
• 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)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain [23.22881271027173]
  We propose S-Diff, inspired by graph-based collaborative filtering.<n>S-Diff maps user interaction vectors into the spectral domain and parameterizes diffusion noise to align with graph frequency.<n>This anisotropic diffusion retains significant low-frequency components, preserving a high signal-to-noise ratio.
  arXiv  Detail & Related papers  (2024-12-31T10:54:41Z)
• Degradation-Noise-Aware Deep Unfolding Transformer for Hyperspectral Image Denoising [9.119226249676501]
  Hyperspectral images (HSIs) are often quite noisy because of narrow band spectral filtering. To reduce the noise in HSI data cubes, both model-driven and learning-based denoising algorithms have been proposed. This paper proposes a Degradation-Noise-Aware Unfolding Network (DNA-Net) that addresses these issues.
  arXiv  Detail & Related papers  (2023-05-06T13:28:20Z)

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.