7 papers
Depth from Dual Differential Defocus and Stereo Consensus
Junjie Luo, Wei Xu, Dylan Chu +2
We introduce D^3S Consensus, a physics-based, closed-form algorithm that unifies depth-from-defocus (DfD) and stereo to achieve highly accurate depth estimation throughout an exten…
Compact single-shot ranging and near-far imaging using metasurfaces
Junjie Luo, Yuxuan Liu, Wei Ting Chen +2
We present a metasurface imaging system capable of simultaneously capturing two images at close range (1-2~cm) and an additional image at long range (about 40~cm) on a shared photo…
Focal Split: Untethered Snapshot Depth from Differential Defocus
Junjie Luo, John Mamish, Alan Fu +4
We introduce Focal Split, a handheld, snapshot depth camera with fully onboard power and computing based on depth-from-differential-defocus (DfDD). Focal Split is passive, avoiding…
Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
Wei Xu, Charles James Wagner, Junjie Luo +1
Extracting depth information from photon-limited, defocused images is challenging because depth from defocus (DfD) relies on accurate estimation of defocus blur, which is fundament…
Depth from Coupled Optical Differentiation
Junjie Luo, Yuxuan Liu, Emma Alexander +1
We propose depth from coupled optical differentiation, a low-computation passive-lighting 3D sensing mechanism. It is based on our discovery that per-pixel object distance can be r…
Generative Quanta Color Imaging
Vishal Purohit, Junjie Luo, Yiheng Chi +3
The astonishing development of single-photon cameras has created an unprecedented opportunity for scientific and industrial imaging. However, the high data throughput generated by…
CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks
Wei Xu, Junjie Luo, Qi Guo
We present CT-Bound, a robust and fast boundary detection method for very noisy images using a hybrid Convolution and Transformer neural network. The proposed architecture decompos…