SATB-VR trains few-step video restoration diffusion models via SNR-aware trajectory blending of predictor outputs with ground-truth and a denoiser-driven consistency loss to achieve favorable performance on benchmarks.
Duo-vsr: Dual-stream distillation for one-step video super-resolution.arXiv preprint arXiv:2603.22271, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending
SATB-VR trains few-step video restoration diffusion models via SNR-aware trajectory blending of predictor outputs with ground-truth and a denoiser-driven consistency loss to achieve favorable performance on benchmarks.