SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation

• URL: http://arxiv.org/abs/2606.11969v1
• Date: Wed, 10 Jun 2026 11:49:54 GMT
• Title: SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
• Abstract summary: Flowmatching has enabled robust text-to-video generation via latent ODE.<n>SpectLoR significantly reduces physical artifacts and enhances motion coherence across multiple benchmarks with minimal computational overhead.
• Score: 39.71466927392354
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow Matching has enabled robust text-to-video generation via latent ODE sampling. However, velocity approximation and numerical discretization errors inevitably accumulate, causing sampling trajectories to drift. Consequently, generated videos often suffer from severe spatiotemporal inconsistencies. Nevertheless, directly correcting these drifted, noisy latents is challenging: (i) timestep-dependent noise obscures reliable structural cues; (ii) spatial interventions risk disrupting intricate local geometry while incurring heavy computational costs. To address this, we propose Spectral Lookahead Rectification (SpecLoR), a plug-and-play inference method that bypasses noise via lookahead prediction, and circumvents spatiotemporal entanglement by shifting corrections to the frequency domain, where universal statistical priors of natural videos are readily available. First, during early sampling stages, SpecLoR looks ahead to estimate the clean latent $z_{t,0}$ and computes its 3D spatiotemporal spectrum. Next, SpecLoR rectifies the amplitude spectrum to match the prior, leaving the phase intact. Finally, the corrected state is re-noised to resume ODE integration. Experiments on Wan2.2 demonstrate that SpecLoR significantly reduces physical artifacts and enhances motion coherence across multiple benchmarks with minimal computational overhead (4 additional NFEs).

Related papers

• GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors [27.10799700736534]
  Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos.<n>We argue that this inefficiency stems from the prevailing reliance on a standard Gaussian source distribution, where consecutive frames are as independent Gaussian noise.<n>We propose GeoFlow, a novel framework designed to achieve efficient driving video generation by harnessing explicit geometric priors.
  arXiv  Detail & Related papers  (2026-08-12T15:57:08Z)
• Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting [21.300422393514804]
  We propose a deterministic framework that reformulates nowcasting as progressive frequency-decoupled refinement.<n>SDIR first extracts a stable low-frequency synoptic skeleton, then iteratively refines high-frequency textures under physical constraints.<n> Experiments on three benchmarks show SDIR significantly outperforms SOTA methods in spatial accuracy.
  arXiv  Detail & Related papers  (2026-06-01T07:34:30Z)
• Bridging Restoration and Generation Manifolds in One-Step Diffusion for Real-World Super-Resolution [22.963799508399365]
  Recent single-step distillation accelerates inference but faces a stark perception-distortion trade-off.<n>We present Adaptive Inversion and Degradation-aware Sampling for Real-ISR (IDaS-SR)<n>IDaS-SR is a one-step framework bridging the deterministic restoration and generation bottlenecks.
  arXiv  Detail & Related papers  (2026-04-27T07:43:00Z)
• GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting [71.12303582606019]
  Continuous Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial and frame rate of videos by arbitrary scale factors.<n>We propose GS-STVSR, an ultra-efficient C-STVSR framework based on 2D Gaussianting (2D-GS)<n>We show that GS-STVSR achieves state-of-the-art quality across all benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T10:11:05Z)
• End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction [74.31251139839047]
  THO is an end-to-end Spatial-Temporal Transformer that predicts human motion and coordinated object motion in a forward fashion from the given video and 3D template.<n> experiments demonstrate that THO operates at an inference speed of 31.5 FPS on a single 4090 GPU, achieving a >600x speedup over prior optimization-based methods.
  arXiv  Detail & Related papers  (2026-03-15T15:21:36Z)
• Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark [22.5556672954071]
  Spectral Compressive Imaging (SCI) has achieved remarkable success, unlocking significant potential for dynamic spectral vision.<n>Existing reconstruction methods, primarily image-based, suffer from two limitations.<n>The frame-by-frame reconstruction paradigm fails to ensure temporal consistency, which is crucial in the video perception.
  arXiv  Detail & Related papers  (2026-02-28T12:11:13Z)
• 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)
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling [76.91310169118408]
  We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines.<n> SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer's self-generated errors into supervisory prompts.<n>We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.
  arXiv  Detail & Related papers  (2025-10-10T09:45:46Z)
• DiTVR: Zero-Shot Diffusion Transformer for Video Restoration [48.97196894658511]
  DiTVR is a zero shot video restoration framework that couples a diffusion transformer with trajectory aware attention and a flow consistent sampler.<n>Our attention mechanism aligns tokens along optical flow trajectories, with particular emphasis on vital layers that exhibit the highest sensitivity to temporal dynamics.<n>The flow guided sampler injects data consistency only into low-frequency bands, preserving high frequency priors while accelerating cache.
  arXiv  Detail & Related papers  (2025-08-11T09:54:45Z)

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.