1 code implementation • 14 Nov 2022 • Byungho Jo, Donghyeon Cho, In Kyu Park, Sungeun Hong
Existing face restoration models have relied on general assessment metrics that do not consider the characteristics of facial regions.
no code implementations • 25 Nov 2021 • Jonathan Samuel Lumentut, In Kyu Park
This task is designed for directly translating a blurry image input into its restored version as output.
no code implementations • ICCV 2021 • Farkhod Makhmudkhujaev, Sungeun Hong, In Kyu Park
Learned personalized age features are identity information that is recalibrated according to the target age.
no code implementations • 23 Dec 2019 • Kyuho Bae, Andre Ivan, Hajime Nagahara, In Kyu Park
To tackle this problem, we propose a deep learning-based method for synthesizing a light field video from a monocular video.
no code implementations • 22 Dec 2019 • Jung Un Yun, In Kyu Park
Recent convolutional neural network (CNN) based method has shown excellent performance by learning mapping relation using pairs of low-resolution (LR) and high-resolution (HR) facial images.
no code implementations • 23 Nov 2019 • Andre Ivan, Williem, In Kyu Park
The conventional method relies on physical-based rendering and a secondary network to solve the angular super-resolution problem.
no code implementations • ICCV 2019 • Xiaowei Yuan, In Kyu Park
In recent decades, 3D morphable model (3DMM) has been commonly used in image-based photorealistic 3D face reconstruction.
1 code implementation • 6 Apr 2019 • Julius Surya Sumantri, In Kyu Park
Conversely, conventional images represent scenes in a single viewing direction with a small or limited field of view (FOV).
no code implementations • 31 Mar 2019 • Jonathan Samuel Lumentut, Tae Hyun Kim, Ravi Ramamoorthi, In Kyu Park
Restoring a sharp light field image from its blurry input has become essential due to the increasing popularity of parallax-based image processing.
no code implementations • 29 Mar 2019 • Andre Ivan, Williem, In Kyu Park
Synthesizing a densely sampled light field from a single image is highly beneficial for many applications.
no code implementations • ECCV 2018 • Dongwoo Lee, Haesol Park, In Kyu Park, Kyoung Mu Lee
Removing camera motion blur from a single light field is a challenging task since it is highly ill-posed inverse problem.
no code implementations • CVPR 2016 • W. Williem, In Kyu Park
To remedy this problem, we present a light field depth estimation method which is more robust to occlusion and less sensitive to noise.
no code implementations • ICCV 2015 • W. Williem, Ramesh Raskar, In Kyu Park
In this paper, we present a joint iterative anaglyph stereo matching and colorization framework for obtaining a set of disparity maps and colorized images.
no code implementations • CVPR 2015 • Christian Simon, In Kyu Park
In this paper, we propose a novel method to remove the reflection on the windscreen in the in-vehicle black box videos.