no code implementations • 21 Sep 2023 • Kiseok Choi, Inchul Kim, Dongyoung Choi, Julio Marco, Diego Gutierrez, Min H. Kim
Existing time-resolved non-line-of-sight (NLOS) imaging methods reconstruct hidden scenes by inverting the optical paths of indirect illumination measured at visible relay surfaces.
no code implementations • CVPR 2023 • Daniel S. Jeon, Andreas Meuleman, Seung-Hwan Baek, Min H. Kim
In this work, we propose a polarimetric iToF imaging method that can capture depth information robustly through scattering media.
no code implementations • CVPR 2023 • Andreas Meuleman, Yu-Lun Liu, Chen Gao, Jia-Bin Huang, Changil Kim, Min H. Kim, Johannes Kopf
For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner.
no code implementations • CVPR 2023 • Donggun Kim, Hyeonjoong Jang, Inchul Kim, Min H. Kim
In this work, we propose a self-supervised learning method that learns bidirectional disparity by utilizing the nature of anisotropic blur kernels in dual-pixel photography.
no code implementations • ICCV 2023 • Jungwoo Kim, Min H. Kim
To tackle this issue, we propose a single-shot HDR demosaicing method that takes time-varying multiple exposures as input and jointly solves both the demosaicing and deghosting problems.
no code implementations • 6 Oct 2022 • Andreas Meuleman, Hakyeong Kim, James Tompkin, Min H. Kim
Fusing RGB stereo and ToF information is a promising direction to overcome these issues, but a key problem remains: to provide high-quality 2D RGB images, the main color sensor's lens is optically stabilized, resulting in an unknown pose for the floating lens that breaks the geometric relationships between the multimodal image sensors.
1 code implementation • 9 Jul 2022 • Inseung Hwang, Daniel S. Jeon, Adolfo Muñoz, Diego Gutierrez, Xin Tong, Min H. Kim
Ellipsometry techniques allow to measure polarization information of materials, requiring precise rotations of optical components with different configurations of lights and sensors.
1 code implementation • SIGGRAPH 2021 • Mustafa B. Yaldiz, Andreas Meuleman, Hyeonjoong Jang, Hyunho Ha, Min H. Kim
Second, a differentiable image simulator creates a training dataset of photorealistic scene images with the deformed markers, being rendered during optimization in a differentiable manner.
no code implementations • CVPR 2022 • Donghun Kang, Hyeonjoong Jang, Jungeon Lee, Chong-Min Kyung, Min H. Kim
However, stereo matching performance on these image formats has been lower than the conventional stereo due to severe image distortion near pole regions.
1 code implementation • 7 Jul 2021 • Numair Khan, Min H. Kim, James Tompkin
We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients.
no code implementations • CVPR 2021 • Hyunho Ha, Joo Ho Lee, Andreas Meuleman, Min H. Kim
Volumetric fusion enables real-time scanning using a conventional RGB-D camera, but its geometry resolution has been limited by the grid resolution of the volumetric distance field and depth registration errors.
no code implementations • CVPR 2021 • Hakyeong Kim, Andreas Meuleman, Daniel S. Jeon, Min H. Kim
However, when an extraordinary-ray (e-ray) image is restored to acquire stereo images, the existing methods suffer from very severe restoration artifacts in stereo images due to a low signal-to-noise ratio of input e-ray image or depth/deconvolution errors.
no code implementations • CVPR 2021 • Andreas Meuleman, Hyeonjoong Jang, Daniel S. Jeon, Min H. Kim
RGB-D imaging prototype composed of a mobile GPU and four fisheye cameras.
1 code implementation • CVPR 2021 • Numair Khan, Min H. Kim, James Tompkin
We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision.
1 code implementation • 9 Sep 2020 • Numair Khan, Min H. Kim, James Tompkin
Previous light field depth estimation methods typically estimate a depth map only for the central sub-aperture view, and struggle with view consistent estimation.
no code implementations • ICCV 2021 • Seung-Hwan Baek, Hayato Ikoma, Daniel S. Jeon, Yuqi Li, Wolfgang Heidrich, Gordon Wetzstein, Min H. Kim
Imaging depth and spectrum have been extensively studied in isolation from each other for decades.
1 code implementation • ICCV 2019 • Inchang Choi, Orazio Gallo, Alejandro Troccoli, Min H. Kim, Jan Kautz
We present Extreme View Synthesis, a solution for novel view extrapolation that works even when the number of input images is small--as few as two.
no code implementations • CVPR 2018 • Daniel S. Jeon, Seung-Hwan Baek, Inchang Choi, Min H. Kim
We present a novel method that can enhance the spatial resolution of stereo images using a parallax prior.
no code implementations • CVPR 2016 • Joo Ho Lee, Inchang Choi, Min H. Kim
In this paper, we propose a patch-based synthesis using a Laplacian pyramid to improve searching correspondence with enhanced awareness of edge structures.
no code implementations • CVPR 2016 • Seung-Hwan Baek, Inchang Choi, Min H. Kim
Since a user specifies the region to be completed in one of multiview photographs casually taken in a scene, the proposed method enables us to complete the set of photographs with geometric consistency by creating or removing structures on the specified region.