Single-Image Fence Removal Using Deep Convolutional Neural Network

Matsui, Takuro; Ikehara, Masaaki

doi:10.1109/access.2019.2960087

Cited by 17 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi focus fence occluded data are simulated by inducing Gaussian blur in clear scenes, and extracted fences. The clear fence superimposed are used as in restoration, while clean images are used as reference [13].…”

Section: Resultsmentioning

confidence: 99%

“…Restoration homographic matrices, dictionary based on k-means labeling, exemplar based inpainting manual initialization Deep learning based methods [11], [12], [13], [14], [15], [16], [17], [18], [19], [20] De-fencing adversarial, structural [21], [22], [23], [24], [25] Fusion multi-scale decomposition, dictionary-learning, nuclear norm regularizer, morphologies constraints, adaptive fusion rules, fractional differential coefficients, geometric sparse coefficients overcomplete dictionary, patch based clustering, single dictionary learning time efficiency, separate fusion and noise removal tasks, information loss due to channel-wise processing Model based methods [26], [27], [28], [29], [30], [31], [32], [33] [34], [35], [36], [37] Fusion SSIM, encoder features, K-means clustering, NSCT, Coupled-Neural-Ps consistency verification photo realistic fusion, blocking artifacts, post processing complete contours; and generator-discriminator setting for prediction of contour completion. In [3], subtraction based on gray-scale binarization is applied on multi-focus auxiliary images to obtain initial mask for image inpainting.…”

Section: Schemesmentioning

confidence: 99%

“…The scheme provides promising results, however, requires multiple GPUs and training data. In [13], regression based method is pro-…”

Section: Schemesmentioning

confidence: 99%

See 2 more Smart Citations

De-Fencing and Multi-Focus Fusion Using Markov Random Field and Image Inpainting

2022

View full text Add to dashboard Cite

Multi-focus image fusion aims at combining source information from differently focused images. Fusion of multi-focus images has great applications in machine vision. The paper focuses on removal of fence occlusions in multi-focus images. The proposed model extracts fence occlusion map using salient image features, and refined by morphological operators. Binary operators, and inpainting methods are used for fence removal and restoration. The proposed model estimates the fence area using statistical characteristics in focused regions. Similarly, binary filtering is used to perform thinning of enlarged areas for optimised restoration. The proposed model employs guided filtering for consistency verification. Fusion and restoration results are compared using several (reference and no-reference based) image quality metrics. Simulations show that proposed scheme achieves better results (visually and quantitatively) as compared to existing state-of-the-art techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Schemesmentioning

confidence: 99%

See 1 more Smart Citation

De-Fencing and Multi-Focus Fusion Using Markov Random Field and Image Inpainting

2022

View full text Add to dashboard Cite

show abstract

“…We evaluate reconstruction quality using SSIM, PSNR and 1-LPIPS (higher is better) for dirt, raindrops and fence obstructions. We compare our method against conventional inpainting methods (CTSDG [Guo et al 2021], LaMa [Suvorov et al 2021]), a method tailored to raindrop degradation (AttentiveGAN [Qian et al 2018]) and a method specialized to fence inpainting (DefenceNet [Matsui and Ikehara 2020]). We further compare to optics-only DOE designs and using the proposed DOE while ablating the neural network.…”

Section: Synthetic Assessmentmentioning

confidence: 99%

Seeing through obstructions with diffractive cloaking

et al. 2022

View full text Add to dashboard Cite

Unwanted camera obstruction can severely degrade captured images, including both scene occluders near the camera and partial occlusions of the camera cover glass. Such occlusions can cause catastrophic failures for various scene understanding tasks such as semantic segmentation, object detection, and depth estimation. Existing camera arrays capture multiple redundant views of a scene to see around thin occlusions. Such multi-camera systems effectively form a large synthetic aperture, which can suppress nearby occluders with a large defocus blur, but significantly increase the overall form factor of the imaging setup. In this work, we propose a monocular single-shot imaging approach that optically cloaks obstructions by emulating a large array. Instead of relying on different camera views, we learn a diffractive optical element (DOE) that performs depth-dependent optical encoding, scattering nearby occlusions while allowing paraxial wavefronts to be focused. We computationally reconstruct unobstructed images from these superposed measurements with a neural network that is trained jointly with the optical layer of the proposed imaging system. We assess the proposed method in simulation and with an experimental prototype, validating that the proposed computational camera is capable of recovering occluded scene information in the presence of severe camera obstruction.

show abstract

“…Removal of obstructions from images is a task particularly close to our task as it deals with less stationary noise [8,9]. Matsui et al [10] use a convolutional neural network similar to our architecture to remove fences from images. Restoration methods differ from our detection task in that explicit detection reporting and evaluation of false positives are not needed when applied as an audio de-noising effect.…”

Section: Related Workmentioning

confidence: 99%

Audio Defect Detection in Music with Deep Networks

Wolff¹,

Mignot²,

Röebel³

2022

Preprint

View full text Add to dashboard Cite

With increasing amounts of music being digitally transferred from production to distribution, automatic means of determining media quality are needed. Protection mechanisms in digital audio processing tools have not eliminated the need of production entities located downstream the distribution chain to assess audio quality and detect defects inserted further upstream. Such analysis often relies on the received audio and scarce meta-data alone. Deliberate use of artefacts such as clicks in popular music as well as more recent defects stemming from corruption in modern audio encodings call for data-centric and contextsensitive solutions for detection. We present a convolutional network architecture following end-to-end encoderdecoder configuration to develop detectors for two exemplary audio defects. A click detector is trained and compared to a traditional signal processing method, with a discussion on context sensitivity. Additional post-processing is used for data augmentation and workflow simulation. The ability of our models to capture variance is explored in a detector for artefacts from decompression of corrupted MP3 compressed audio. For both tasks we describe the synthetic generation of artefacts for controlled detector training and evaluation. We evaluate our detectors on the large open-source Free Music Archive (FMA) and genrespecific datasets.

show abstract

Single-Image Fence Removal Using Deep Convolutional Neural Network

Cited by 17 publications

References 24 publications

De-Fencing and Multi-Focus Fusion Using Markov Random Field and Image Inpainting

De-Fencing and Multi-Focus Fusion Using Markov Random Field and Image Inpainting

Seeing through obstructions with diffractive cloaking

Audio Defect Detection in Music with Deep Networks

Contact Info

Product

Resources

About