DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution

• URL: http://arxiv.org/abs/2605.30431v1
• Date: Thu, 28 May 2026 18:00:14 GMT
• Title: DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
• Abstract summary: We introduce a training-free framework that enhances distorted and low-resolution videos by decoupling conditional and unconditional branches in time.<n>Our proposed Decoupled Time Guidance (DTG) evaluates the unconditional branch at a cleaner diffusion timestep.<n>To facilitate evaluation, we curate GenWarp480, a benchmark of 4,400 distorted 480p videos synthesized from diverse text-to-video models.
• Score: 11.720438605063748
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in video diffusion models has enabled remarkable generative fidelity, yet leveraging these priors for restoration remains limited by the strong coupling between conditional and unconditional branches in standard classifier-free guidance. We introduce a training-free framework that enhances distorted and low-resolution videos by decoupling these signals in time. Our proposed Decoupled Time Guidance (DTG) evaluates the unconditional branch at a cleaner diffusion timestep, providing a lookahead prior that preserves geometry while suppressing replication of warped content. This temporal bias is annealed throughout sampling, allowing the model to transition from structure correction to detail refinement without retraining. Combined with any off-the-shelf restoration module in a plug-and-play manner, our approach improves perceptual coherence and restores plausible structure in AIgenerated and real-world videos alike. To facilitate evaluation, we curate GenWarp480, a benchmark of 4,400 distorted 480p videos synthesized from diverse text-to-video models. GenWarp480 focuses on characteristic generative degradations such as warped faces, body misalignments, and spatial artifacts, providing a purpose-built testbed for assessing robustness to generative errors. Extensive experiments demonstrate that our method achieves significant improvements in structural fidelity and temporal stability without any model training.

Related papers

• Video Generation with Predictive Latents [50.3100375593545]
  Video Autoencoder (Eational) enables latent video generative modeling by mapping the visual world into compact latent spaces.<n>How to enhance the diffusability of video latents remains a critical and unresolved challenge.<n>We introduce a simple and effective predictive reconstruction objective that unifies predictive learning with video reconstruction.
  arXiv  Detail & Related papers  (2026-05-04T01:30:04Z)
• Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity [57.83511884904928]
  We explore methods to accelerate training for autoregressive video generation models through empirical analyses.<n>Our results reveal that while training on fewer video frames significantly reduces training time, it also exacerbates error accumulation and introduces inconsistencies in the generated videos.<n>Inspired by Lipschitz continuity, we propose a Representation Continuity (ReCo) strategy to improve the consistency of generated videos.
  arXiv  Detail & Related papers  (2026-04-08T09:43:03Z)
• Your Pre-trained Diffusion Model Secretly Knows Restoration [55.7186754179308]
  We show that pre-trained diffusion models inherently possess restoration behavior, which can be unlocked by directly learning prompt embeddings.<n>We introduce our lightweight learned prompts on the pre-trained WAN video model and FLUX image models, converting them into high-performing restoration models.
  arXiv  Detail & Related papers  (2026-04-06T17:59:04Z)
• Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence [30.812937732503457]
  Free-GVC is a training-free generative video compression framework.<n>Our method operates at the group-of-pictures level, encoding video segments into a compact latent space.<n>Experiments show that Free-GVC achieves an average of 93.29% BD-Rate reduction in DISTS over the latest neural DCVC-RT.
  arXiv  Detail & Related papers  (2026-02-10T15:12:51Z)
• All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations [102.94052335735326]
  All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model.<n>Existing approaches primarily focus on frame-wise degradation variation, overlooking the temporal continuity that naturally exists in real-world degradation processes.<n>We introduce the Smoothly Evolving Unknown Degradations (SEUD) scenario, where both the active degradation set and degradation intensity change continuously over time.
  arXiv  Detail & Related papers  (2026-01-02T02:20:57Z)
• CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videos [17.81372151946937]
  CreativeVR is a diffusion-prior-guided video restoration framework for AI-generated (AIGC) and real videos with severe structural and temporal artifacts.<n>Our deep-adapter-based method exposes a single precision knob that controls how strongly the model follows the input.<n>CreativeVR achieves state-of-the-art results on videos with severe artifacts and performs competitively on standard video restoration benchmarks.
  arXiv  Detail & Related papers  (2025-12-12T22:03:14Z)
• Improving Temporal Consistency and Fidelity at Inference-time in Perceptual Video Restoration by Zero-shot Image-based Diffusion Models [5.61537470581101]
  We address the challenge of improving temporal coherence in video restoration using zero-shot image-based diffusion models.<n>We propose two complementary inference-time strategies: Perceptual Straightening Guidance (PSG) and Ensemble Sampling (MPES)
  arXiv  Detail & Related papers  (2025-10-29T11:40:06Z)
• LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restoration [3.2944592608677614]
  We propose LVTINO, the first zero-shot or plug-and-play inverse solver for high definition video restoration with priors encoded by VCMs.<n>Our conditioning mechanism bypasses the need for automatic differentiation and achieves state-of-the-art video reconstruction quality with only a few neural function evaluations.
  arXiv  Detail & Related papers  (2025-10-01T18:10:08Z)
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion [67.94300151774085]
  We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models.<n>It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs.
  arXiv  Detail & Related papers  (2025-06-09T17:59:55Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  New tokenizer, Diffusion Conditioned-based Gene Tokenizer, replaces GAN-based decoder with conditional diffusion model.<n>We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch.<n>Even a scaled-down version of CDT (3$times inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)

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.