Yonsei University · 情報科学
Professor Hyunjung Shim's research lab specializes in computational imaging and computer vision, with a focus on advanced 3D reconstruction, image denoising, and face modeling under complex lighting and material conditions. The lab develops deep learning-based methods for enhancing image quality in low-dose and noisy imaging scenarios, particularly using generative adversarial networks (GANs) and perceptual losses. It also pioneers techniques for face relighting and realistic face synthesis without explicit 3D shape reconstruction, leveraging subspace models of reflectance and probabilistic diffuse/specular modeling. The lab’s work bridges the gap between physical imaging limitations and perceptually accurate rendering, especially for challenging materials like translucency and varying surface reflectance.
Figures are computed from collected data and may differ slightly.
The evaluation results using tSNR, NPS, and MTF indicate that VGG-loss-based CNNs are more effective than those without VGG loss for natural denoising of low-dose images and WGAN-GP loss improves the denoising performance of VGG-loss-based CNNs, which corresponds with the qualitative evaluation.
We present a new approach to face relighting by jointly estimating the pose, reflectance functions, and lighting from as few as one image of a face. Upon such estimation, we can synthesize the face image under any prescribed new lighting condition. In contrast to commonly used face shape models or shape-dependent models, we neither recover nor assume the 3-D face shape during the estimation process. Instead, we train a pose- and pixel-dependent subspace model of the reflectance function using a
In the presence of nonlinearity in the CNN, the proposed CNN-based model observer showed better performance than other linear observers.
Translucency introduces great challenges to 3-D acquisition because of complicated light behaviors such as refraction and transmittance. In this paper, we describe the development of a unified 3-D data acquisition framework that reconstructs translucent objects using a single commercial time-of-flight (ToF) camera. In our capture scenario, we record a depth map and intensity image of the scene twice using a static ToF camera; first, we capture the depth map and intensity image of an arbitrary ba
A time-of-flight (ToF) depth sensor produces noisy range data due to scene properties such as surface materials and reflectivity. Sensor measurement frequently includes either a saturated or severely noisy depth and effective depth accuracy is far below its ideal specification. In this paper, we propose a hybrid exposure technique for depth imaging in a ToF sensor so to improve the depth quality. Our method automatically determines an optimal depth for each pixel using two exposure conditions. T
This paper presents a novel approach to automatic face modeling for realistic synthesis from an unknown face image, using a probabilistic face diffuse model and a generic face specular map. We construct a probabilistic face diffuse model for estimating the albedo and normals of the input face. Then, we develop a generic face specular map for estimating the specularity of face. Using the estimated albedo, normal and specular information, we can synthesize the face under arbitrary lighting and vie
A light probe is commonly used for measuring the illumination of a real scene. Instead of equipping a man-made light probe such as a mirror ball, we propose to use a face in images as a natural light probe. To that end, we construct a statistical reflectance model for faces and use this model to extract the lighting and the reflectance field of an input face. With an iterative procedure, we can obtain the lighting condition from an unknown face image. As a byproduct of this procedure, we also es
Open papers in the app to read, cite, and organize with AI.
