arXiv subjects

Menghan Xia

Publications and source records attributed to Menghan Xia.

39 records · Page 3Linked to original sources

arXiv2021

Exploiting Aliasing for Manga Restoration

As a popular entertainment art form, manga enriches the line drawings details with bitonal screentones. However, manga resources over the Internet usually show screentone artifacts because of inappropriate scanning/rescaling resolution. In this paper, we propose an innovative two-stage method to restore quality bitonal manga from degraded ones. Our key observation is that the aliasing induced by downsampling bitonal screentones can be utilized as informative clues to infer the original resolution and screentones. First, we predict the target resolution from the degraded manga via the Scale Estimation Network (SE-Net) with spatial voting scheme. Then, at the target resolution, we restore the region-wise bitonal screentones via the Manga Restoration Network (MR-Net) discriminatively, depending on the degradation degree. Specifically, the original screentones are directly restored in pattern-identifiable regions, and visually plausible screentones are synthesized in pattern-agnostic regions. Quantitative evaluation on synthetic data and visual assessment on real-world cases illustrate the effectiveness of our method.

eess.IV↗

arXiv2021

A Learned Compact and Editable Light Field Representation

Light fields are 4D scene representation typically structured as arrays of views, or several directional samples per pixel in a single view. This highly correlated structure is not very efficient to transmit and manipulate (especially for editing), though. To tackle these problems, we present a novel compact and editable light field representation, consisting of a set of visual channels (i.e. the central RGB view) and a complementary meta channel that encodes the residual geometric and appearance information. The visual channels in this representation can be edited using existing 2D image editing tools, before accurately reconstructing the whole edited light field back. We propose to learn this representation via an autoencoder framework, consisting of an encoder for learning the representation, and a decoder for reconstructing the light field. To handle the challenging occlusions and propagation of edits, we specifically designed an editing-aware decoding network and its associated training strategy, so that the edits to the visual channels can be consistently propagated to the whole light field upon reconstruction.Experimental results show that our proposed method outperforms related existing methods in reconstruction accuracy, and achieves visually pleasant performance in editing propagation.

cs.CV↗

arXiv2020

Mononizing Binocular Videos

This paper presents the idea ofmono-nizingbinocular videos and a frame-work to effectively realize it. Mono-nize means we purposely convert abinocular video into a regular monocular video with the stereo informationimplicitly encoded in a visual but nearly-imperceptible form. Hence, wecan impartially distribute and show the mononized video as an ordinarymonocular video. Unlike ordinary monocular videos, we can restore from itthe original binocular video and show it on a stereoscopic display. To start,we formulate an encoding-and-decoding framework with the pyramidal de-formable fusion module to exploit long-range correspondences between theleft and right views, a quantization layer to suppress the restoring artifacts,and the compression noise simulation module to resist the compressionnoise introduced by modern video codecs. Our framework is self-supervised,as we articulate our objective function with loss terms defined on the input:a monocular term for creating the mononized video, an invertibility termfor restoring the original video, and a temporal term for frame-to-framecoherence. Further, we conducted extensive experiments to evaluate ourgenerated mononized videos and restored binocular videos for diverse typesof images and 3D movies. Quantitative results on both standard metrics anduser perception studies show the effectiveness of our method.

eess.IV↗