Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Kim, Soo Ye"'
Autor:
Tarrés, Gemma Canet, Lin, Zhe, Zhang, Zhifei, Zhang, Jianming, Song, Yizhi, Ruta, Dan, Gilbert, Andrew, Collomosse, John, Kim, Soo Ye
Compositing an object into an image involves multiple non-trivial sub-tasks such as object placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and shadow/reflection generation. Recent generative image compositing metho
Externí odkaz:
http://arxiv.org/abs/2409.04559
Autor:
Song, Yizhi, Zhang, Zhifei, Lin, Zhe, Cohen, Scott, Price, Brian, Zhang, Jianming, Kim, Soo Ye, Zhang, He, Xiong, Wei, Aliaga, Daniel
Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, t
Externí odkaz:
http://arxiv.org/abs/2403.10701
Autor:
Cha, Junghun, Haider, Ali, Yang, Seoyun, Jin, Hoeyeong, Yang, Subin, Uddin, A. F. M. Shahab, Kim, Jaehyoung, Kim, Soo Ye, Bae, Sung-Ho
A significant volume of analog information, i.e., documents and images, have been digitized in the form of scanned copies for storing, sharing, and/or analyzing in the digital world. However, the quality of such contents is severely degraded by vario
Externí odkaz:
http://arxiv.org/abs/2402.05350
This paper firstly presents old photo modernization using multiple references by performing stylization and enhancement in a unified manner. In order to modernize old photos, we propose a novel multi-reference-based old photo modernization (MROPM) fr
Externí odkaz:
http://arxiv.org/abs/2304.04461
Autor:
Song, Yizhi, Zhang, Zhifei, Lin, Zhe, Cohen, Scott, Price, Brian, Zhang, Jianming, Kim, Soo Ye, Aliaga, Daniel
Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore, annotating traini
Externí odkaz:
http://arxiv.org/abs/2212.00932
Autor:
Kim, Soo Ye, Zhang, Jianming, Niklaus, Simon, Fan, Yifei, Chen, Simon, Lin, Zhe, Kim, Munchurl
Depth maps are used in a wide range of applications from 3D rendering to 2D image effects such as Bokeh. However, those predicted by single image depth estimation (SIDE) models often fail to capture isolated holes in objects and/or have inaccurate bo
Externí odkaz:
http://arxiv.org/abs/2206.03048
Autor:
Kim, Soo Ye, Aberman, Kfir, Kanazawa, Nori, Garg, Rahul, Wadhwa, Neal, Chang, Huiwen, Karnad, Nikhil, Kim, Munchurl, Liba, Orly
Although deep learning has enabled a huge leap forward in image inpainting, current methods are often unable to synthesize realistic high-frequency details. In this paper, we propose applying super-resolution to coarsely reconstructed outputs, refini
Externí odkaz:
http://arxiv.org/abs/2012.09401
Blind super-resolution (SR) methods aim to generate a high quality high resolution image from a low resolution image containing unknown degradations. However, natural images contain various types and amounts of blur: some may be due to the inherent d
Externí odkaz:
http://arxiv.org/abs/2012.08103
Super-resolution (SR) has been widely used to convert low-resolution legacy videos to high-resolution (HR) ones, to suit the increasing resolution of displays (e.g. UHD TVs). However, it becomes easier for humans to notice motion artifacts (e.g. moti
Externí odkaz:
http://arxiv.org/abs/1912.07213
Joint learning of super-resolution (SR) and inverse tone-mapping (ITM) has been explored recently, to convert legacy low resolution (LR) standard dynamic range (SDR) videos to high resolution (HR) high dynamic range (HDR) videos for the growing need
Externí odkaz:
http://arxiv.org/abs/1909.04391