paper-with-me

홈 › Papers

Very Long Natural Scenery Image Prediction by Outpainting

2019-12-29 · ICCV 2019 10 · Zongxin Yang, Jian Dong, Ping Liu, Yi Yang, Shuicheng Yan

Comparing to image inpainting, image outpainting receives less attention due to two challenges in it. The first challenge is how to keep the spatial and content consistency between generated images and original input. The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input. To solve the two problems, we devise some innovative modules, named Skip Horizontal Connection and Recurrent Content Transfer, and integrate them into our designed encoder-decoder structure. By this design, our network can generate highly realistic outpainting prediction effectively and efficiently. Other than that, our method can generate new images with very long sizes while keeping the same style and semantic content as the given input. To test the effectiveness of the proposed architecture, we collect a new scenery dataset with diverse, complicated natural scenes. The experimental results on this dataset have demonstrated the efficacy of our proposed network. The code and dataset are available from https://github.com/z-x-yang/NS-Outpainting.

📄 PDF Abstract BibTeX arXiv:1912.12688

Code (1)

z-x-yang/NS-Outpainting 공식 구현 tf

Tasks

DecoderImage InpaintingImage OutpaintingPrediction

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Data relativistic uncertainty framework for low-illumination anime scenery image enhancement

2025-12-26 · Yiquan Gao, John See arxiv

By contrast with the prevailing works of low-light enhancement in natural images and videos, this study copes with the low-illumination quality degradation in anime scenery images to bridge the domain gap. For such an un…

Image Enhancement

Generator Pyramid for High-Resolution Image Inpainting

2020-12-04 · Leilei Cao, Tong Yang, Yixu Wang, Bo Yan 외

Inpainting high-resolution images with large holes challenges existing deep learning based image inpainting methods. We present a novel framework -- PyramidFill for high-resolution image inpainting task, which explicitly…

Image InpaintingTexture SynthesisVocal Bursts Intensity Prediction

Controllable Longer Image Animation with Diffusion Models

2024-05-27 · Qiang Wang, Minghua Liu, Junjun Hu, Fan Jiang 외

Generating realistic animated videos from static images is an important area of research in computer vision. Methods based on physical simulation and motion prediction have achieved notable advances, but they are often l…

Image Animationmotion predictionVideo Generation

Behavior-Semantic Scenery Description (BSSD) of Road Networks for Automated Driving

2022-02-10 · Moritz Lippert, Felix Glatzki, Hermann Winner

The safety approval of Highly Automated Vehicles (HAV) is economically infeasible with current approaches. For verification and validation, it is essential to describe the intended behavior of an HAV in the development p…

Measuring Atmospheric Scattering from Digital Images of Urban Scenery using Temporal Polarization-Based Vision

2014-07-14 · Tarek El-Gaaly, Joshua Gluckman

Particulate Matter (PM) is a form of air pollution that visually degrades urban scenery and is hazardous to human health and the environment. Current monitoring devices are limited in measuring average PM over large area…