Wide-Context Semantic Image Extrapolation
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i.e., extending image borders with plausible structure and details. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues are size expansion and one-side constraints. We propose a semantic regeneration network with several special contributions and use multiple spatial related losses to address these issues. Our results contain consistent structures and high-quality textures. Extensive experiments are conducted on various possible alternatives and related methods. We also explore the potential of our method for various interesting applications that can benefit research in a variety of fields.
Code (2)
Tasks
Image InpaintingImage OutpaintingSeeing Beyond the VisibleSimilar Papers 제목 키워드 기반
Context-aware Padding for Semantic Segmentation
Zero padding is widely used in convolutional neural networks to prevent the size of feature maps diminishing too fast. However, it has been claimed to disturb the statistics at the border. As an alternative, we propose a…
SegmentationSemantic SegmentationSemIE: Semantically-aware Image Extrapolation
We propose a semantically-aware novel paradigm to perform image extrapolation that enables the addition of new object instances. All previous methods are limited in their capability of extrapolation to merely extending t…
ObjectPanoptic SegmentationSegmentationSemantic SegmentationSpiral Generative Network for Image Extrapolation
In this paper, motivated by human natural ability to perceive unseen surroundings imaginatively, we propose a novel Spiral Generative Network, SpiralNet, to perform image extrapolation in a spiral manner, which regards e…
Complex-Valued Frequency Selective Extrapolation for Fast Image and Video Signal Extrapolation
Signal extrapolation tasks arise in miscellaneous manners in the field of image and video signal processing. But, due to the widespread use of low-power and mobile devices, the computational complexity of an algorithm pl…
MiscellaneousAccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation
Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate method for patch-wise higher-resolution…
Image GenerationLocal Distortion