Fractional-Order Adaptive Motion Magnification: Phase-Reliability Weighting for Noise-Constrained Video Amplification

• URL: http://arxiv.org/abs/2609.04502v1
• Date: Thu, 03 Sep 2026 21:43:22 GMT
• Title: Fractional-Order Adaptive Motion Magnification: Phase-Reliability Weighting for Noise-Constrained Video Amplification
• Abstract summary: 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.
• Score: 51.56484100374058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Eulerian video amplification boosts sub-pixel motion by band-pass filtering per-pixel intensity traces and applying a uniform gain. That gain ignores local structure, so sensor noise is amplified together with the signal, especially in textureless regions where the monogenic phase is unreliable. We propose FrAM (Fractional-order Adaptive Motion Magnification), a pipeline developed first offline and then as a causal stream. It replaces the constant temporal gain with a Grünwald--Letnikov derivative of fractional order, giving continuous control over high-frequency emphasis, and replaces the uniform spatial gain with a per-pixel weight derived from the local amplitude of the monogenic signal. On a controlled synthetic sequence split into textured and flat halves, FrAM matches the amplification of the Eulerian baseline while keeping flat-region temporal noise at the input level. The reduction holds across an eightfold range of input noise levels. Real videos show improved spatial selectivity and lower background noise in every case. The causal reformulation cuts the per-frame cost by two orders of magnitude, reaching 69\,fps at 640$\times$480.

Related papers

• Noise structuring in fixed-depth Trotter simulation: stationary channels and observable-level depolarization [0.0]
  We analyze fixed-depth Trotter simulation as a method for structuring hardware noise in digital many-body dynamics.<n>For local faults, we show that, once propagated faults lose memory of their insertion layer, the noisy circuit factorizes into ideal evolution.<n>Our results also reveal limitations of naive zero-noise extrapolatin strategies based on oversimplified functions.
  arXiv  Detail & Related papers  (2026-07-20T13:33:59Z)
• 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)
• DDSP-QbE++: Improving Speech Quality for Speech Anonymisation for Atypical Speech [4.129225533930966]
  We propose improvements to the excitation stage of the subtractive synthesisP-QbE training pipeline for voice conversion.<n>We incorporate explicit voicing detection to gate the harmonic excitation, suppressing the periodic component in unvoiced regions and replacing it with filtered noise.<n>The proposed approach is lightweight, differentiable, and integrates seamlessly into the existingP-QbE training pipeline with no additional learnable parameters.
  arXiv  Detail & Related papers  (2026-04-10T11:58:58Z)
• NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration [20.351955950047348]
  Diffusion-based Plug-and-Play (NFC) methods produce images with high quality but often suffer from reduced fidelity data.<n>We propose Frequency Diffusion-led Sampling (NFCDS), a modulation mechanism for reverse diffusion noise.
  arXiv  Detail & Related papers  (2026-01-29T04:10:45Z)
• EuleroDec: A Complex-Valued RVQ-VAE for Efficient and Robust Audio Coding [18.199202388702144]
  Most frequency-domain neural codecs disregard phase information or encode it as two separate real-valued channels, limiting spatial fidelity.<n>This entails the need to introduce adversarial discriminators at the expense of convergence speed and training stability.<n>In this work we introduce an end-to-end complex-valued RVQ-VAE audio that preserves magnitude-phase coupling across the entire analysis-quantization-synthesis pipeline.
  arXiv  Detail & Related papers  (2026-01-24T16:34:07Z)
• NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation [88.09231548061295]
  Phase-Preserving Diffusion -PD is a model-agnostic reformulation of the diffusion process.<n>-PD preserves input phase while randomizing magnitude, enabling structure-aligned generation without architectural changes.<n>-PD adds no inference-time cost and is compatible with any diffusion model for images or videos.
  arXiv  Detail & Related papers  (2025-12-04T18:59:18Z)
• PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs [57.790910044227935]
  Video LLMs suffer from temporal inconsistency: small shifts in frame timing can flip attention and suppress relevant frames.<n>We present Phase Aggregated Smoothing (PAS), a training-free mechanism that applies small opposed phase offsets across heads and then aggregates their outputs.<n>Our analysis shows that the RoPE rotated logit can be approximated as a content dot product scaled by a time kernel; smoothing this kernel yields Lipschitz stability of attention to small temporal shifts; multi phase averaging attenuates high frequency ripples while preserving per-head spectra under Nyquist-valid sampling.
  arXiv  Detail & Related papers  (2025-11-14T05:56:47Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• Autonomous coherence protection of a two-level system in a fluctuating environment [68.8204255655161]
  We re-examine a scheme originally intended to remove the effects of static Doppler broadening from an ensemble of non-interacting two-level systems (qubits) We demonstrate that this scheme is far more powerful and can also protect a single (or even an ensemble) qubit's energy levels from noise which depends on both time and space.
  arXiv  Detail & Related papers  (2023-02-08T01:44:30Z)

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.