SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending

• URL: http://arxiv.org/abs/2606.28677v1
• Date: Sat, 27 Jun 2026 01:32:16 GMT
• Title: SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending
• Abstract summary: We present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor.<n>We show that SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.
• Score: 55.764018145256216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While diffusion models excel in video restoration, their reliance on extensive iterative steps limits efficiency. Conversely, aggressive single-step distillation often compromises fine texture recovery. To achieve an optimal balance, we present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor, explicitly bypassing early low signal-to-noise ratio (SNR) steps. However, naive joint training of the predictor and the denoiser inherently introduces a severe train-inference discrepancy. To resolve this, we propose the SNR-Aware Trajectory Blending (SATB) strategy. During the forward process, SATB constructs the noisy input by dynamically blending the predictor's output with the ground-truth trajectory based on the SNRs. This forces the denoiser to robustly compensate for initial prediction errors while smoothly converging to the clean data manifold. Furthermore, we introduce a Denoiser-Driven Consistency (DDC) loss, leveraging the concurrently updated denoiser as a dynamic evaluator to explicitly align internal features and boost predictor accuracy. Extensive experiments demonstrate that, under flexible few-step inference regimes (\eg, $\le 5$ steps), SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.

Related papers

• MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution [50.60539317126614]
  MeanSR learns an LR-conditioned average velocity field to directly capture the finite-time transition from noisy inputs to plausible HR outputs.<n>Experiments show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency.
  arXiv  Detail & Related papers  (2026-08-10T10:33:18Z)
• PedestrianDiffusion: Multimodal Generative Denoising and Dense State Estimation for Inertial Navigation [1.8620637029128544]
  PedestrianDiffusion is a generative framework that reformulates dense 6D state estimation as a continuous conditional denoising process.<n>It achieves state-of-the-art performance, exhibiting unprecedented robustness to impulse perturbations and coupled 6D kinematic drift.<n>This work provides a rigorous algorithmic blueprint for next-generation Neural Inertial Measurement Units (N-IMUs)
  arXiv  Detail & Related papers  (2026-07-03T14:04:30Z)
• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• 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)
• Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training [32.42657582329756]
  Conditional Diffusion Models are powerful surrogates for emulating complex dynamics.<n>They often fail to match the accuracy of neural emulators for high-precision tasks.<n>We address two critical limitations of autoregressive PDE diffusion models: their sub-temporal single-step accuracy and the prohibitive computational cost of unrolled training.
  arXiv  Detail & Related papers  (2026-04-09T15:21:31Z)
• Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining [4.511561231517167]
  Diffusion/score-based models have emerged as powerful generative priors for solving inverse problems.<n>We propose Zero-shot Adaptive Diffusion Sampling (ZADS), a test-time optimization method that tunes fidelity weights across arbitrary noise schedules.<n>ZADS consistently outperforms both traditional compressed sensing and recent diffusion-based methods.
  arXiv  Detail & Related papers  (2025-09-11T22:22:32Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step [119.18813219518042]
  Super-resolution (SR) methods based on diffusion models exhibit promising results. But their practical application is hindered by the substantial number of required inference steps. We propose a simple yet effective method for achieving single-step SR generation, named SinSR.
  arXiv  Detail & Related papers  (2023-11-23T16:21:29Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• 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)

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.