M
Min H. Kim
Researcher at KAIST
Publications - 90
Citations - 2304
Min H. Kim is an academic researcher from KAIST. The author has contributed to research in topics: Hyperspectral imaging & Computer science. The author has an hindex of 24, co-authored 81 publications receiving 1560 citations. Previous affiliations of Min H. Kim include University College London & SK Hynix.
Papers
More filters
Posted Content
View-consistent 4D Light Field Depth Estimation
TL;DR: This work proposes a method to compute depth maps for every sub-aperture image in a light field in a view consistent way, and achieves competitive quantitative metrics and qualitative performance on both synthetic and real-world light fields.
Proceedings ArticleDOI
Consistent scene illumination using a chromatic flash
Min H. Kim,Jan Kautz +1 more
TL;DR: This work proposes a simple but powerful method to automatically match the correlated color temperature of the auxiliary flash light with that of scene illuminations allowing for well-lit photographs while maintaining the atmosphere of the scene.
Journal ArticleDOI
Progressive Acquisition of SVBRDF and Shape in Motion
TL;DR: A simultaneous acquisition method of SVBRDF and shape allowing us to capture the material appearance of deformable objects in motion using a single RGBD camera is proposed and yields complete material appearance parameters.
Proceedings ArticleDOI
Urban Image Stitching using Planar Perspective Guidance
TL;DR: The results validate the effectiveness of the image stitching method over state-of-the-art projective warp methods in terms of planar perspective, and allow us to enhance linear perspective structures while warping multiple urban images with grid-like structures.
Proceedings Article
View-consistent 4D Light Field Depth Estimation.
TL;DR: In this paper, the authors propose a method to compute depth maps for every sub-aperture image in a light field in a view consistent way, where they define depth edges via EPIs, diffuse these edges spatially within the central view, and finally disoccluded regions are completed by diffusion in EPI space.