SwiftVR achieves real-time generative video restoration at 1080p on consumer GPUs (26 FPS on RTX 5090) and higher resolutions on H100 via efficient dense attention and chunk-wise autoencoding.
Dove: Efficient one- step diffusion model for real-world video super-resolution
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
OSDEnhancer delivers state-of-the-art real-world space-time video super-resolution via one-step diffusion with temporal coherence and texture enrichment LoRAs plus a deformable recurrent VAE decoder.
Stream-DiffVSR enables practical low-latency video super-resolution by combining a four-step distilled denoiser, auto-regressive temporal guidance, and a temporal processor in a strictly causal pipeline.
AVSR-Diff uses a decoupled diffusion framework with TGFR and SAFR modules to deliver temporally consistent arbitrary-scale video super-resolution that outperforms fixed-scale and arbitrary-scale baselines.
SmartDirector generates cinematic videos via Director-Gen for low-res keyframe-conditioned output followed by Director-SR refinement using high-res keyframes, trained on curated movie sequences.
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
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.
The NTIRE 2026 challenge releases the KwaiVIR benchmark for short-form UGC video restoration and reports strong results from 12 teams using generative models on both subjective and objective tracks.
OASIS reduces redundancy in diffusion models for real-world video super-resolution via attention specialization routing and progressive training, delivering state-of-the-art quality with 6.2x faster inference than prior one-step baselines.
Existing video quality models show only moderate correlation with subjective ratings for diffusion-based video super-resolution, with CNN-based full-reference models performing best but none accurate enough to replace human evaluation.
citing papers explorer
No citing papers match the current filters.