Inpainting of Wide-Baseline Multiple Viewpoint Video

Gilbert, Andrew; Trumble, Matthew; Hilton, Adrian; Collomosse, John

doi:10.1109/tvcg.2018.2889297

Cited by 5 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early works attempt to solve the problem by either diffusionbased or patch-based algorithms [1,2,3,9,10,11]. A diffusionbased algorithm propagates contextual information from boundaries into holes in the isophotes direction [1,9].…”

Section: Introductionmentioning

confidence: 99%

Aggregated Contextual Transformations for High-Resolution Image Inpainting

Zeng¹,

Fu²,

Chao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Image inpainting that completes large free-form missing regions in images is a promising yet challenging task. State-of-the-art approaches have achieved significant progress by taking advantage of generative adversarial networks (GAN). However, these approaches can suffer from generating distorted structures and blurry textures in high-resolution images (e.g., 512 × 512). The challenges mainly drive from (1) image content reasoning from distant contexts, and (2) fine-grained texture synthesis for a large missing region. To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting. Specifically, to enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block. The AOT blocks aggregate contextual transformations from various receptive fields, allowing to capture both informative distant image contexts and rich patterns of interest for context reasoning. For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task. Such a training objective forces the discriminator to distinguish the detailed appearances of real and synthesized patches, and in turn facilitates the generator to synthesize clear textures. Extensive comparisons on Places2, the most challenging benchmark with 1.8 million high-resolution images of 365 complex scenes, show that our model outperforms the state-of-the-art by a significant margin in terms of FID with 38.60% relative improvement. A user study including more than 30 subjects further validates the superiority of AOT-GAN. We further evaluate the proposed AOT-GAN in practical applications, e.g., logo removal, face editing, and object removal. Results show that our model achieves promising completions in the real-world. We release code and models in https://github.com/researchmm/AOT-GAN-for-Inpainting.

show abstract