Source-linked AI summary

Rethinking Coarse-to-Fine Approach in Single Image Deblurring

Sung-Jin Cho, Seo-Won Ji, Jun-Pyo Hong, Seung-Won Jung, Sung-Jea Ko

arXiv:2108.05054v2cs.CVcs.AI

TL;DR

Conventional coarse-to-fine deblurring networks are computationally costly, while lightweight designs may sacrifice state-of-the-art accuracy. MIMO-UNet uses one multi-input, multi-output U-Net with asymmetric feature fusion and outperforms conventional methods in speed and accuracy.

  • Problem

    Conventional deblurring networks have high computational and memory costs, while lightweight architectures may not achieve comparable state-of-the-art accuracy.

  • Method

    MIMO-UNet replaces stacked sub-networks with one U-Net using multi-scale inputs, multi-scale outputs, and asymmetric feature fusion for coarse-to-fine deblurring.

  • Results

    MIMO-UNet outperforms conventional methods in both deblurring speed and accuracy on the GoPro and RealBlur datasets.

  • Takeaways & Limitations

    A single modified U-Net provides a simpler coarse-to-fine deblurring design with reported gains in computational efficiency and restoration accuracy.

  • Takeaways & Limitations

    Runtime comparisons use released test code measured on the authors’ PC alongside runtimes reported in other papers.

Abstract

from arXiv · show

Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Conventional methods typically stack sub-networks with multi-scale input images and gradually improve sharpness of images from the bottom sub-network to the top sub-network, yielding inevitably high computational costs. Toward a fast and accurate deblurring network design, we revisit the coarse-to-fine strategy and present a multi-input multi-output U-net (MIMO-UNet). The MIMO-UNet has three distinct features. First, the single encoder of the MIMO-UNet takes multi-scale input images to ease the difficulty of training. Second, the single decoder of the MIMO-UNet outputs multiple deblurred images with different scales to mimic multi-cascaded U-nets using a single U-shaped network. Last, asymmetric feature fusion is introduced to merge multi-scale features in an efficient manner. Extensive experiments on the GoPro and RealBlur datasets demonstrate that the proposed network outperforms the state-of-the-art methods in terms of both accuracy and computational complexity. Source code is available for research purposes at https://github.com/chosj95/MIMO-UNet.

1. Introduction

Single-image deblurring must recover sharp images despite motion-induced blur that harms visual quality and vision systems, while conventional coarse-to-fine networks incur high computational and memory costs. MIMO-UNet revisits this strategy with a single encoder-decoder network whose multi-scale inputs and multi-output decoder enable efficient coarse-to-fine restoration.

  • Motivation: Single-image deblurring recovers a latent sharp image from blur caused by camera or object motion, whose artifacts degrade visual quality and vision-system performance.The passage specifically identifies surveillance and autonomous driving as affected systems.
  • Prior Work: CNN-based methods evolved from two-stage blur-kernel estimation and deconvolution frameworks toward end-to-end learning of blurry-sharp image relationships.DeepDeblur is identified as a pioneering deep multi-scale CNN for dynamic-scene deblurring.
  • Problem: Conventional coarse-to-fine methods increase computational complexity and memory usage, limiting deployment in cost- and time-sensitive environments.Examples include mobile devices, vehicles, and robots.
  • Proposed Method: MIMO-UNet is a single encoder-decoder U-shaped network designed to handle multi-scale blur with low computational complexity.The paper presents it as a reconsideration of the coarse-to-fine scheme.
  • Proposed Method: Its multi-output single decoder produces multiple deblurred images and mimics stacked sub-networks by guiding gradual coarse-to-fine recovery of latent sharp images.Experiments report superiority over state-of-the-art methods in PSNR and computational complexity.

2. Related works

Related work commonly adopts coarse-to-fine deblurring, progressively recovering sharp images through multiple scales, sub-networks, or repeated U-shaped networks. DeepDeblur established this direction, followed by PSS-NSC and MT-RNN variants that modify feature connections, parameter sharing, or recurrent processing.

  • Conventional image deblurring methods reviewed here adopt a coarse-to-fine strategy for gradual recovery of latent sharp images.
  • DeepDeblur: DeepDeblur directly learns blurry-sharp image relations end-to-end and uses multiple stacked sub-networks receiving differently scaled inputs.Outputs from coarser sub-networks are concatenated with finer-scale inputs to enable progressive reconstruction.
  • GoPro dataset: The GoPro dataset constructs blurry images by averaging successive sharp frames captured at 240 fps and uses the middle sampled frame as ground truth.
  • PSS-NSC: PSS-NSC retains DeepDeblur’s multi-sub-network design but structures each sub-network as an encoder-decoder U-Net with symmetric skip connections.It additionally introduces parameter selective sharing across sub-networks.
  • MT-RNN: MT-RNN repeats a single U-shaped network seven times and transfers decoder feature maps from each iteration to the next encoder.Each iteration predicts an averaged image formed with a different M, decreasing as processing proceeds.

3. Proposed method

MIMO-UNet revisits coarse-to-fine deblurring with a single U-Net that processes multi-scale inputs, produces multi-scale outputs, and enables cross-scale feature fusion. Its design also uses multi-scale content supervision and a frequency reconstruction loss to improve restoration.

  • Architecture: MIMO-UNet is a single U-Net with three encoder blocks and decoder blocks, modified for efficient multi-scale deblurring through MISE, MOSD, and AFF.The architecture is organized around the paper’s three stated special features.
  • Multi-scale input: Each encoder block receives a blurry image at a different scale and combines downsampled-image features with features from the preceding encoder level.This complementary multi-scale input is intended to help handle diverse image blurs effectively.
  • Multi-scale output: Each decoder block receives intermediate supervision, allowing its multi-scale feature map to be mapped into an output image that mimics multi-stacked sub-networks.The mapping function is implemented with a single convolutional layer.
  • Asymmetric feature fusion: AFF modules take outputs from all encoder blocks, align different scales through up- and down-sampling, and deliver fused features to corresponding decoder blocks.This design allows information flow from different scales within a single U-Net, so each decoder block can exploit multi-scale features.
  • Training objective: The network uses multi-scale L1 content loss and introduces MSFR loss, which measures L1 distance between multi-scale ground-truth and deblurred images in the frequency domain.The frequency-domain comparison uses the fast Fourier transform, and the final loss sets λ = 0.1.

4. Experiments

Experiments on GoPro and RealBlur evaluate MIMO-UNet’s accuracy, efficiency, component contributions, and utility for object detection. The study compares three model variants with state-of-the-art methods and finds consistent benefits from the proposed components and preprocessing use.

  • Experimental Setup: The models were trained on 2,103 GoPro and 3,758 RealBlur blurred–sharp image pairs, then tested on 1,111 and 980 pairs, respectively.GoPro testing used a model trained only on the GoPro training set.
  • Comparisons: MIMO-UNet, MIMO-UNet+, and MIMO-UNet++ evaluate increasing capacity and geometric self-ensemble within a single architecture.The variants use 8 or 20 residual blocks per encoder and decoder block, while MIMO-UNet++ estimates the resultant image using geometric self-ensemble.
  • Comparisons: MIMO-UNet was compared with state-of-the-art deblurring networks using runtime measurements from released test code and runtimes reported in the papers.Author-released models were reproduced for GoPro and RealBlur comparisons, including SRN, PSS-NSC, DMPHN, MT-RNN, MPRNet, and DeblurGAN-v2.
  • Ablation Studies: FAM achieved the highest performance among feature-fusion methods, while combining MISE with MOSD improved PSNR by 0.05 dB and AFF improved it by 0.17 dB over baseline.Using AFF with MISE increased the gain to 0.23 dB; MISE, MOSD, and AFF together achieved 0.30 dB higher PSNR.
  • Object Detection: MIMO-UNet++ was also evaluated as a deblurring preprocessing method for object detection against PSS-NSC and DMPHN using author-provided codes.The evaluation used sharp-image bounding boxes as ground truth and focused on car, person, and potted plant classes present in GoPro images.

5. Conclusion

The paper proposes a fast, accurate image deblurring network that replaces stacked coarse-to-fine subnetworks with a single, simpler U-Net. Its encoder accepts multi-scale inputs, while its decoder outputs multi-scale deblurred images during decoding.

  • The proposed network targets fast and accurate image deblurring.
  • A single U-Net replaces stacked sub-networks for coarse-to-fine deblurring, simplifying the architecture.
  • The encoder takes multi-scale input images and combines features from different sources.
  • The decoder outputs multi-scale deblurred images during decoding.
Loading 2108.05054v2…