Pith. sign in

REVIEW 5 cited by

Revisiting Temporal Modeling for Video Super-resolution

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2008.05765 v2 pith:ACROMPJD submitted 2020-08-13 eess.IV cs.CV

classification eess.IVcs.CV
keywords super-resolutionvideomethodstemporalmodelingproposedresultscompare
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR methods have been proposed, it is hard to directly compare these methods since the different loss functions and training datasets have a significant impact on the super-resolution results. In this work, we carefully study and compare three temporal modeling methods (2D CNN with early fusion, 3D CNN with slow fusion and Recurrent Neural Network) for video super-resolution. We also propose a novel Recurrent Residual Network (RRN) for efficient video super-resolution, where residual learning is utilized to stabilize the training of RNN and meanwhile to boost the super-resolution performance. Extensive experiments show that the proposed RRN is highly computational efficiency and produces temporal consistent VSR results with finer details than other temporal modeling methods. Besides, the proposed method achieves state-of-the-art results on several widely used benchmarks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration

    cs.CV 2025-07 conditional novelty 6.0 of 10

    IP-FVR restores degraded face videos with consistent identity by conditioning a video diffusion model on a reference photo of the same person.

  2. Omnidirectional Video Super-Resolution using Deep Learning

    cs.MM 2025-06 conditional novelty 5.0 of 10

    A new 360-degree video dataset and a recurrent attention-based super-resolution model, S3PO, are introduced and shown to improve PSNR on omnidirectional video benchmarks over several prior VSR models.

  3. Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution

    cs.CV 2025-06 conditional novelty 5.0 of 10

    SCST reports the best perceptual quality (LPIPS/DISTS) on four synthetic benchmarks and the best no-reference quality scores on the real-world VideoLQ benchmark by adding spatio-temporal Mamba and contrastive ControlN...

  4. A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A bottom-up survey of efficiency optimization techniques for DNN-based video analytics, spanning storage, computing, algorithms, and applications.

  5. A Survey of Deep Learning Video Super-Resolution

    eess.IV 2025-06 conditional novelty 3.0 of 10

    A literature survey that proposes a multi-level component taxonomy for deep-learning video super-resolution models and catalogs reported methods, datasets, and benchmarks.

Pith tools