paper-with-me

Papers

Semantically-Adaptive Upsampling for Layout-to-Image Translation

2021-01-01 · Hao Tang, Nicu Sebe

We propose the Semantically-Adaptive UpSampling (SA-UpSample), a general and highly effective upsampling method for the layout-to-image translation task. SA-UpSample has three advantages: 1) Global view. Unlike traditional upsampling methods (e.g., Nearest-neighbor) that only exploit local neighborhoods, SA-UpSample can aggregate semantic information in a global view. 2) Semantically adaptive. Instead of using a fixed kernel for all locations (e.g., Deconvolution), SA-UpSample enables semantic class-specific upsampling via generating adaptive kernels for different locations. 3) Efficient. Unlike Spatial Attention which uses a fully-connected strategy to connect all the pixels, SA-UpSample only considers the most relevant pixels, introducing little computational overhead. We observe that SA-UpSample achieves consistent and substantial gains on six popular datasets. The source code will be made publicly available.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

Layout-to-Image Translation with Double Pooling Generative Adversarial Networks

2021-08-29 · Hao Tang, Nicu Sebe

In this paper, we address the task of layout-to-image translation, which aims to translate an input semantic layout to a realistic image. One open challenge widely observed in existing methods is the lack of effective se…

Translation

Geometry Aligned Variational Transformer for Image-conditioned Layout Generation

2022-09-02 · Yunning Cao, Ye Ma, Min Zhou, Chuanbin Liu 외

Layout generation is a novel task in computer vision, which combines the challenges in both object localization and aesthetic appraisal, widely used in advertisements, posters, and slides design. An accurate and pleasant…

Layout DesignLayout GenerationObject Localization

BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation

2026-05-11 · Qi Yang, Xiangyao Ma, Xiao Wang, Hao Wang 외 arxiv

As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing document translation pipelines face a tension between linguistic proces…

Attribution Upsampling should Redistribute, Not Interpolate

2026-03-17 · Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat, Prayag Tiwari 외 arxiv

Attribution methods in explainable AI rely on upsampling techniques that were designed for natural images, not saliency maps. Standard bilinear and bicubic interpolation systematically corrupts attribution signals throug…

Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion

2023-02-13 · Xi Zhang, Xiaolin Wu

Ultra high resolution (UHR) images are almost always downsampled to fit small displays of mobile end devices and upsampled to its original resolution when exhibited on very high-resolution displays. This observation moti…

DecoderImage Compression