FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction

• URL: http://arxiv.org/abs/2605.06509v1
• Date: Thu, 07 May 2026 16:21:34 GMT
• Title: FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
• Abstract summary: Video diffusion models perform well in short-video synthesis, but suffer from content drift, temporal inconsistency, and over-smoothed dynamics.<n>We propose FreeSpec, a training-free spectral reconstruction framework for long-video generation.<n>Experiments on Wan2.1 and LTX-Video demonstrate that FreeSpec improves long-video generation, especially for temporal dynamics.
• Score: 28.81130393371554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video diffusion models perform well in short-video synthesis, but their training-free extension to long videos often suffers from content drift, temporal inconsistency, and over-smoothed dynamics. Existing methods improve temporal consistency by combining a global branch with a local branch, but they often further decompose appearance consistency and temporal dynamics within each branch using predefined criteria. This assignment is unreliable when appearance and action progression are tightly coupled, such as in camera motion and sequential motion. We analyze the video temporal extension issue from a singular-spectrum perspective and show that enlarged self-attention windows induce spectral concentration: spectral energy becomes dominated by a few low-rank singular directions, preserving coarse structure but suppressing high-rank spatial details and motion-rich temporal variations. To mitigate this problem, we propose FreeSpec, a training-free spectral reconstruction framework for long-video generation. FreeSpec decomposes global and local features with singular value decomposition, and uses the global branch as low-rank spectral guidance and the local branch as a high-rank reconstruction basis. This spectrum-level fusion avoids the rigid feature partitioning of previous decomposition rules, preserving long-range consistency while better retaining spatial details and temporal dynamics. Experiments on Wan2.1 and LTX-Video demonstrate that FreeSpec improves long-video generation, especially for temporal dynamics, while maintaining strong visual quality and temporal consistency. Project demo: https://fdchen24.github.io/FreeSpec-Website/.

Related papers

• ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation [38.28031393950813]
  Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes.<n>Existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts.<n>We propose ourname, a Gaussian splatting based framework for volumetric video reconstruction.
  arXiv  Detail & Related papers  (2026-08-31T03:09:16Z)
• Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model [33.214927542512555]
  Diff-VF is a framework that converts short-video diffusion backbones into long-video generators without modifying or fine-tuning the base model.<n>VBench-Long evaluation results show that Diff-VF achieves a more favorable balance between temporal coherence and motion diversity than base models.
  arXiv  Detail & Related papers  (2026-08-06T12:53:46Z)
• FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring [38.650762310010734]
  We propose FreqForcing, a training-free framework that addresses error accumulation in long-video generation via Spectral Self-Anchoring (SSA)<n>Our FreqForcing extends Self-Forcing pretrained on 5s clips to two-minute generation, achieving 24x extrapolation.
  arXiv  Detail & Related papers  (2026-07-29T16:38:47Z)
• SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition [49.508770157706486]
  We propose SRENet to learn both global context and fine-grained temporal dynamics of motion from a frequency perspective for action recognition.<n>SRENet achieves state-of-the-art performance, validating the effectiveness of frequency modeling in point cloud-based action understanding.
  arXiv  Detail & Related papers  (2026-06-02T05:11:47Z)
• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• LoL: Longer than Longer, Scaling Video Generation to Hour [50.945885467651216]
  This work achieves the first demonstration of real-time, streaming, and infinite-length video generation with little quality decay.<n>As an illustration, we generate continuous videos up to 12 hours in length, which, to our knowledge, is among the longest publicly demonstrated results in streaming video generation.
  arXiv  Detail & Related papers  (2026-01-23T17:21:35Z)
• Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability [21.927814986478356]
  We present a statistical analysis of video VAE latent spaces and identify two properties essential for diffusion training.<n>We propose two lightweight, backbone-agnostic regularizers: Local Correlation Regularization and Latent Masked Reconstruction.<n> Experiments show that our Spectral-Structured VAE achieves a $3times$ speedup in text-to-video convergence and a 10% gain in video reward, outperforming strong open-source VAEs.
  arXiv  Detail & Related papers  (2025-12-05T03:20:02Z)
• HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling [52.10845971383909]
  HieraMamba is a hierarchical architecture that preserves temporal structure and semantic richness across scales.<n>It sets a new state-of-the-art on Ego4D-NLQ, MAD, and TACoS, demonstrating precise, temporally faithful localization in long, untrimmed videos.
  arXiv  Detail & Related papers  (2025-10-27T06:13:07Z)
• LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE [16.561410415129778]
  LongScape is a hybrid framework that combines intra-chunk diffusion denoising with inter-chunk autoregressive causal generation.<n>Our core innovation is an action-guided, variable-length chunking mechanism that partitions video based on the semantic context of robotic actions.
  arXiv  Detail & Related papers  (2025-09-26T02:47:05Z)
• FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion [24.48220892418698]
  FreeLong is a training-free framework designed to balance the frequency distribution of long video features during the denoising process.<n>FreeLong achieves this by blending global low-frequency features, which capture holistic semantics across the full video, with local high-frequency features extracted from short temporal windows.<n>FreeLong++ extends FreeLong into a multi-branch architecture with multiple attention branches, each operating at a distinct temporal scale.
  arXiv  Detail & Related papers  (2025-06-30T18:11:21Z)
• Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion [116.40704026922671]
  First-in-first-out (FIFO) video diffusion, built on a pre-trained text-to-video model, has recently emerged as an effective approach for tuning-free long video generation.<n>We propose Ouroboros-Diffusion, a novel video denoising framework designed to enhance structural and content (subject) consistency.
  arXiv  Detail & Related papers  (2025-01-15T18:59:15Z)
• FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention [57.651429116402554]
  This paper investigates a straightforward and training-free approach to extend an existing short video diffusion model for consistent long video generation. We find that directly applying the short video diffusion model to generate long videos can lead to severe video quality degradation. Motivated by this, we propose a novel solution named FreeLong to balance the frequency distribution of long video features during the denoising process.
  arXiv  Detail & Related papers  (2024-07-29T11:52:07Z)
• Generating Long Videos of Dynamic Scenes [66.56925105992472]
  We present a video generation model that reproduces object motion, changes in camera viewpoint, and new content that arises over time. A common failure case is for content to never change due to over-reliance on inductive biases to provide temporal consistency.
  arXiv  Detail & Related papers  (2022-06-07T16:29:51Z)

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.