Pith. sign in

REVIEW 4 cited by

Partial Large Kernel CNNs for Efficient 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 2404.11848 v1 pith:77C6HMPI submitted 2024-04-18 cs.CV

classification cs.CV
keywords largecnnskerneldomainsuper-resolutiontransformerscomparedcomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Recently, in the super-resolution (SR) domain, transformers have outperformed CNNs with fewer FLOPs and fewer parameters since they can deal with long-range dependency and adaptively adjust weights based on instance. In this paper, we demonstrate that CNNs, although less focused on in the current SR domain, surpass Transformers in direct efficiency measures. By incorporating the advantages of Transformers into CNNs, we aim to achieve both computational efficiency and enhanced performance. However, using a large kernel in the SR domain, which mainly processes large images, incurs a large computational overhead. To overcome this, we propose novel approaches to employing the large kernel, which can reduce latency by 86\% compared to the naive large kernel, and leverage an Element-wise Attention module to imitate instance-dependent weights. As a result, we introduce Partial Large Kernel CNNs for Efficient Super-Resolution (PLKSR), which achieves state-of-the-art performance on four datasets at a scale of $\times$4, with reductions of 68.1\% in latency and 80.2\% in maximum GPU memory occupancy compared to SRFormer-light.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Edge-Cloud Collaborative Reconstruction via Structure-Aware Latent Diffusion for Downstream Remote Sensing Perception

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    SALD decouples remote sensing images into compressed payload plus structural prior at the edge and uses structure-gated diffusion on the cloud to improve super-resolution and downstream detection under extreme bandwid...

  2. Large Kernel Modulation Network for Efficient Image Super-Resolution

    cs.CV 2025-08 conditional novelty 5.0 of 10

    LKMN, a pure CNN for efficient image super-resolution, reports better PSNR than current lightweight models while running faster than Transformer-based competitors on standard benchmarks.

  3. LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution

    eess.IV 2025-08 conditional novelty 4.0 of 10

    A CNN-based super-resolution model with decomposed large kernels and partial channel processing matches or beats lightweight transformer models at a fraction of the inference time.

  4. The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

    cs.CV 2026-04 unverdicted novelty 2.0 of 10

    The NTIRE 2026 mobile real-world image super-resolution challenge received 16 valid submissions and overviews methods balancing image quality with mobile execution speed.

Pith tools