FADRA: Frequency-Aware Diffusion with Residual Adaptation for Video Face Restoration

• URL: http://arxiv.org/abs/2607.06389v1
• Date: Tue, 07 Jul 2026 15:24:42 GMT
• Title: FADRA: Frequency-Aware Diffusion with Residual Adaptation for Video Face Restoration
• Abstract summary: Video face restoration (VFR) aims to recover high-quality and temporally consistent facial details from severely degraded video sequences.<n>We propose FADRA, a frequency-aware diffusion framework with iterative residual adaptation specifically tailored for robust VFR.<n>We show that FADRA recovers better facial structures and produces more temporally consistent videos than state-of-the-art methods.
• Score: 19.325369139066925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video face restoration (VFR) aims to recover high-quality and temporally consistent facial details from severely degraded video sequences; however, existing methods still struggle to balance spatial fidelity and temporal coherence under complex degradations. To address this, we propose FADRA, a frequency-aware diffusion framework with iterative residual adaptation specifically tailored for robust VFR. We first leverage the strong temporal consistency of a pre-trained text-to-video diffusion model and introduce lightweight LoRA adapters together with a Low-Quality (LQ) Pixel-Alignment Feature Fusion module to efficiently adapt the frozen generative prior to the VFR task. To further adapt the frozen diffusion backbone to the downstream VFR task beyond LoRA-based adaptation, we introduce a Repeated Residual Adaptation Head (RRAH) for step-wise residual refinement after the diffusion backbone. To make this refinement explicitly guided by the degraded observation, RRAH further takes the LQ latent together with the current velocity prediction as input, allowing the model to repeatedly revisit LQ cues and predict residual updates at each flow-matching step. This LQ-guided repeated residual adaptation helps recover fine facial details while preserving the inherent temporal priors of the pre-trained model. Furthermore, to ensure the structural integrity of perceptually important details, we introduce a Frequency-Aware Loss that provides explicit supervision across multiple spectral bands, emphasizing visually sensitive frequency components that are crucial for perceptual quality and prone to temporal jittering. Extensive experiments demonstrate that FADRA recovers better facial structures and produces more temporally consistent videos than state-of-the-art methods, leading to clear gains in both quantitative metrics and visual perception.

Related papers

• Making Every Step Count: Spatio-Temporal Information Allocation for Imaging Inverse Problems [63.904793414062816]
  We introduce two complementary and training-free components, i.e., Spectrum-based Scheduling (SAS) and Measurement-Prioritized Attention (MPA)<n>SAS distributes the available NFEs over flow time according to the spectrum and logSNR geometry, thus better balancing semantic exploration and detail refinement.<n>MPA guides information toward weakly constrained regions, thereby enhancing semantic and structural fidelity.
  arXiv  Detail & Related papers  (2026-08-12T07:39:22Z)
• Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features [51.5076190312734]
  Video Super-Resolution approaches suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity.<n>We propose a novelly Guided diffusion model with Aligned Features for Video Super-Resolution (DGAF-VSR)<n>Experiments on synthetic and real-world datasets demonstrate that DGAF-VSR surpasses state-of-the-art methods in key aspects of VSR.
  arXiv  Detail & Related papers  (2025-11-21T03:40:45Z)
• 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)
• 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)
• Temporal-Consistent Video Restoration with Pre-trained Diffusion Models [51.47188802535954]
  Video restoration (VR) aims to recover high-quality videos from degraded ones.<n>Recent zero-shot VR methods using pre-trained diffusion models (DMs) suffer from approximation errors during reverse diffusion and insufficient temporal consistency.<n>We present a novel a Posterior Maximum (MAP) framework that directly parameterizes video frames in the seed space of DMs, eliminating approximation errors.
  arXiv  Detail & Related papers  (2025-03-19T03:41:56Z)
• 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)
• Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution [15.197746480157651]
  We propose an effective real-world VSR algorithm by leveraging the strength of pre-trained latent diffusion models. We exploit the temporal dynamics in LR videos to guide the diffusion process by optimizing the latent sampling path with a motion-guided loss. The proposed motion-guided latent diffusion based VSR algorithm achieves significantly better perceptual quality than state-of-the-arts on real-world VSR benchmark datasets.
  arXiv  Detail & Related papers  (2023-12-01T14:40:07Z)
• Intrinsic Temporal Regularization for High-resolution Human Video Synthesis [59.54483950973432]
  temporal consistency is crucial for extending image processing pipelines to the video domain. We propose an effective intrinsic temporal regularization scheme, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful " INTERnet" capable of generating $512times512$ resolution human action videos.
  arXiv  Detail & Related papers  (2020-12-11T05:29:45Z)

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.