Pith. sign in

REVIEW 3 cited by

Revisiting Image Deblurring with an Efficient ConvNet

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 2302.02234 v1 pith:XMOH4LUZ submitted 2023-02-04 cs.CV

classification cs.CV
keywords deblurringimagenetworkperformancebettercnnscomparablecomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Image deblurring aims to recover the latent sharp image from its blurry counterpart and has a wide range of applications in computer vision. The Convolution Neural Networks (CNNs) have performed well in this domain for many years, and until recently an alternative network architecture, namely Transformer, has demonstrated even stronger performance. One can attribute its superiority to the multi-head self-attention (MHSA) mechanism, which offers a larger receptive field and better input content adaptability than CNNs. However, as MHSA demands high computational costs that grow quadratically with respect to the input resolution, it becomes impractical for high-resolution image deblurring tasks. In this work, we propose a unified lightweight CNN network that features a large effective receptive field (ERF) and demonstrates comparable or even better performance than Transformers while bearing less computational costs. Our key design is an efficient CNN block dubbed LaKD, equipped with a large kernel depth-wise convolution and spatial-channel mixing structure, attaining comparable or larger ERF than Transformers but with a smaller parameter scale. Specifically, we achieve +0.17dB / +0.43dB PSNR over the state-of-the-art Restormer on defocus / motion deblurring benchmark datasets with 32% fewer parameters and 39% fewer MACs. Extensive experiments demonstrate the superior performance of our network and the effectiveness of each module. Furthermore, we propose a compact and intuitive ERFMeter metric that quantitatively characterizes ERF, and shows a high correlation to the network performance. We hope this work can inspire the research community to further explore the pros and cons of CNN and Transformer architectures beyond image deblurring tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. 4KAgent: Agentic Any Image to 4K Super-Resolution

    cs.CV 2025-07 reject novelty 6.0 of 10

    An agentic pipeline that plans and executes image restoration from a toolbox of pretrained models to upscale arbitrary images to 4K, reporting state-of-the-art results on many benchmarks.

  2. The RealDefocus Benchmark for Defocus Deblurring

    cs.CV 2026-07 conditional novelty 4.0 of 10

    RealDefocus, built from the authors' RealBokeh captures, becomes a standardized SIDD benchmark; training on it improves RealDOF generalization over DPDD-S across ten architectures.

  3. Moir\'e Zero: An Efficient and High-Performance Neural Architecture for Moir\'e Removal

    cs.CV 2025-07 conditional novelty 4.0 of 10

    MZNet reports state-of-the-art moiré removal on high-resolution benchmarks with a U-Net combining multi-scale dual attention, multi-shape large-kernel convolutions, and fused skip connections.

Pith tools