Painting Outside the Box: Image Outpainting with GANs

Sabini, Mark; Rusak, Gili

doi:10.48550/arxiv.1808.08483

Cited by 12 publications

(27 citation statements)

References 6 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lack of stochasticity is also observed in image completion (Cai & Wei, 2019;Zheng et al, 2019). Other works address the so-called outpainting subtasks (Sabini & Rusak, 2018;Wang et al, 2019a;Yang et al, 2019b). To our knowledge, none of these methods produce promising results in the presence of free-form large-scale missing regions.…”

Section: Related Workmentioning

confidence: 98%

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Zhao

Cui²,

Sheng

et al. 2021

Preprint

View full text Add to dashboard Cite

Numerous task-specific variants of conditional generative adversarial networks have been developed for image completion. Yet, a serious limitation remains that all existing algorithms tend to fail when handling large-scale missing regions. To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations. Also, due to the lack of good quantitative metrics for image completion, we propose the new Paired/Unpaired Inception Discriminative Score (P-IDS/U-IDS), which robustly measures the perceptual fidelity of inpainted images compared to real images via linear separability in a feature space. Experiments demonstrate superior performance in terms of both quality and diversity over state-of-the-art methods in free-form image completion and easy generalization to image-to-image translation.Code is available at https://github.com/zsyzzsoft/co-mod-gan.

show abstract

Section: Related Workmentioning

confidence: 98%

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Zhao

Cui²,

Sheng

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…While a majority of self-supervision methods is validated on classification tasks, different kinds of features fit better for different tasks [40]. Therefore, specific self-supervision methods have been proposed for better performance in different tasks: optical flow [12,22], reflection removal [17,35], image inpainting [25,29], image outpainting [26,28], and light estimation [5,27].…”

Section: Related Workmentioning

confidence: 99%

“…Compared to PSL, our method is simple and general, since we do not constrain our method to a specific task. To compare with the approach, we train the model on the beach dataset [26], which contains 10,515 images of nature landscapes.…”

Section: Comparison To Psl [16]mentioning

confidence: 99%

See 1 more Smart Citation

In-N-Out: Towards Good Initialization for Inpainting and Outpainting

Jo¹,

Im²,

Yoon³

2021

Preprint

View full text Add to dashboard Cite

In computer vision, recovering spatial information by filling in masked regions, e.g., inpainting, has been widely investigated for its usability and wide applicability to other various applications: image inpainting, image extrapolation, and environment map estimation. Most of them are studied separately depending on the applications. Our focus, however, is on accommodating the opposite task, e.g., image outpainting, which would benefit the target applications, e.g., image inpainting. Our self-supervision method, In-N-Out, is summarized as a training approach that leverages the knowledge of the opposite task into the target model. We empirically show that In-N-Out -which explores the complementary information -effectively takes advantage over the traditional pipelines where only task-specific learning takes place in training. In experiments, we compare our method to the traditional procedure and analyze the effectiveness of our method on different applications: image inpainting, image extrapolation, and environment map estimation. For these tasks, we demonstrate that In-N-Out consistently improves the performance of the recent works with In-N-Out self-supervision to their training procedure. Also, we show that our approach achieves better results than an existing training approach for outpainting.

show abstract

“…A LTHOUGH image inpainting has been widely studied, its cousin, image outpainting, has been relatively unexplored [1]. Image inpainting algorithms aim to predict relatively small missing or corrupted parts of the interiors of images, based on evidence from surrounding pixels.…”

Section: Introductionmentioning

confidence: 99%

180-degree Outpainting from a Single Image

Ying,

Bovik

2020

Preprint

View full text Add to dashboard Cite

Presenting context images to a viewer's peripheral vision is one of the most effective techniques to enhance immersive visual experiences. However, most images only present a narrow view, since the field-of-view (FoV) of standard cameras is small. To overcome this limitation, we propose a deep learning approach that learns to predict a 180-degree panoramic image from a narrow-view image. Specifically, we design a foveated framework that applies different strategies on near-periphery and mid-periphery regions. Two networks are trained separately, and then are employed jointly to sequentially perform narrow-to-90 • generation and 90 • -to-180 • generation. The generated outputs are then fused with their aligned inputs to produce expanded equirectangular images for viewing. Our experimental results show that single-view-to-panoramic image generation using deep learning is both feasible and promising.

show abstract

Painting Outside the Box: Image Outpainting with GANs

Cited by 12 publications

References 6 publications

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

In-N-Out: Towards Good Initialization for Inpainting and Outpainting

180-degree Outpainting from a Single Image

Contact Info

Product

Resources

About