127 citations · 229 across the 11 of their papers we have counts for
7 papers · 1 filter
Self-Calibrating, Fully Differentiable NLOS Inverse Rendering
Kiseok Choi, Inchul Kim, Dongyoung Choi +3
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…
Progressively Optimized Local Radiance Fields for Robust View Synthesis
Andreas Meuleman, Yu-Lun Liu, Chen Gao +4
We present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing…
DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers
Mustafa B. Yaldiz, Andreas Meuleman, Hyeonjoong Jang +2
Fiducial markers have been broadly used to identify objects or embed messages that can be detected by a camera. Primarily, existing detection methods assume that markers are printe…
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
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. Our proposed approach is based around the idea tha…
Differentiable Diffusion for Dense Depth Estimation from Multi-view Images
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 super…
View-consistent 4D Light Field Depth Estimation
Numair Khan, Min H. Kim, James Tompkin
We propose a method to compute depth maps for every sub-aperture image in a light field in a view consistent way. Previous light field depth estimation methods typically estimate a…
Extreme View Synthesis
Inchang Choi, Orazio Gallo, Alejandro Troccoli +2
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. In this context, occlusions and…