REVIEW 7 cited by
Video Super-Resolution Transformer
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
read the original abstract
Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Recently, Transformer has been gaining popularity due to its parallel computing ability for sequence-to-sequence modeling. Thus, it seems to be straightforward to apply the vision Transformer to solve VSR. However, the typical block design of Transformer with a fully connected self-attention layer and a token-wise feed-forward layer does not fit well for VSR due to the following two reasons. First, the fully connected self-attention layer neglects to exploit the data locality because this layer relies on linear layers to compute attention maps. Second, the token-wise feed-forward layer lacks the feature alignment which is important for VSR since this layer independently processes each of the input token embeddings without any interaction among them. In this paper, we make the first attempt to adapt Transformer for VSR. Specifically, to tackle the first issue, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information. For the second issue, we design a bidirectional optical flow-based feed-forward layer to discover the correlations across different video frames and also align features. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. The code will be available at https://github.com/caojiezhang/VSR-Transformer.
Forward citations
Cited by 7 Pith papers
-
MambaVSR: Content-Aware Scanning State Space Model for Video Super-Resolution
A state-space model for video super-resolution gains long-range spatiotemporal modeling by ordering tokens according to a content-aware, spectral-clustering-based scan.
-
Decoupling Cross-Modality Manifold Discrepancy: Leveraging Visible Diffusion Priors for Infrared Super-Resolution
Shift-IISR steers a frozen visible-pretrained diffusion model toward the infrared manifold via global representation modulation and local Sobel-edge refinement, improving infrared super-resolution consistency.
-
FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring
A non-recurrent, exposure-conditioned video super-resolution and deblurring model achieves state-of-the-art results on synthetic multi-exposure benchmarks and generalizes to GoPro and real-world videos.
-
NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices
NanoVSR reaches 28.64 dB PSNR at 27.2 FPS on Jetson Orin NX (25W) for 4× VSR by reparameterized convolutions and progressive implicit alignment without optical flow.
-
WaveHiT-SR: Hierarchical Wavelet Network for Efficient Image Super-Resolution
WaveHiT-SR embeds discrete wavelet transforms into hierarchical transformer blocks, producing efficient super-resolution models with modest PSNR gains over SwinIR and SRFormer baselines.
-
LiftVSR: Lifting Image Diffusion to Video Super-Resolution via Hybrid Temporal Modeling with Only 4$\times$RTX 4090s
LiftVSR combines short-segment dynamic temporal attention, a long-term attention memory cache, and Diffusion Forcing style asymmetric sampling to achieve strong perceptual video super-resolution scores with dramatical...
-
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution
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...
Discussion (0). Sign in to comment.