• Corpus ID: 237532384

Towards Non-Line-of-Sight Photography

  title={Towards Non-Line-of-Sight Photography},
  author={Jiayong Peng and Fangzhou Mu and Ji Hyun Nam and Siddeshwar Raghavan and Yin Li and Andreas Velten and Zhiwei Xiong},
Non-line-of-sight (NLOS) imaging is based on capturing the multi-bounce indirect reflections from the hidden objects. Active NLOS imaging systems rely on the capture of the time of flight of light through the scene, and have shown great promise for the accurate and robust reconstruction of hidden scenes without the need for specialized scene setups and prior assumptions. Despite that existing methods can reconstruct 3D geometries of the hidden scene with excellent depth resolution, accurately… 

Figures and Tables from this paper


Real-time Non-line-of-Sight imaging of dynamic scenes
It is shown that SPAD (Single-Photon Avalanche Diode) array detectors with a total of just 28 pixels combined with a specifically extended Phasor Field reconstruction algorithm can reconstruct live real-time videos of non-retro-reflective NLOS scenes.
Non-line-of-sight Imaging with Partial Occluders and Surface Normals
This work introduces a factored NLOS light transport representation that accounts for partial occlusions and surface normals and develops a factorization approach for inverse time-resolved light transport and demonstrates high-fidelity NLOS reconstructions for challenging scenes both in simulation and with an experimental NLOS imaging system.
Non–line-of-sight imaging over 1.43 km
Hardware and software solutions are developed and adopted to increase the standoff distance of NLOS imaging from meter to kilometer range, which is about three orders of magnitude longer than previous experiments, enabling the demonstration ofNLOS imaging and real-time tracking of hidden objects over a distance of 1.43 km.
Beyond Volumetric Albedo — A Surface Optimization Framework for Non-Line-Of-Sight Imaging
An analysis-by-synthesis framework that can reconstruct complex shape and reflectance of an NLOS object at a level of detail significantly exceeding what is possible with previous volumetric reconstruction methods is introduced.
Fast Back-Projection for Non-Line of Sight Reconstruction
This work proposes a new back-projection technique for NLOS reconstruction, up to a thousand times faster than previous work, with almost no quality loss, and demonstrates the efficiency and quality of the technique compared against previous methods.
Confocal non-line-of-sight imaging based on the light-cone transform
The resolution bounds of NLOS imaging are quantified, its potential for real-time tracking is demonstrated, and efficient algorithms that incorporate image priors and a physically accurate noise model are derived.
Deep Non-Line-of-Sight Reconstruction
This paper devise a tailored autoencoder architecture, trained end-to-end, that maps transient images directly to a depth-map representation and demonstrates that the feed-forward network employed, even if trained solely on synthetic data, is able to obtain results competitive with previous, model-based optimization methods, while being orders of magnitude faster.
Non-line-of-sight imaging using phasor-field virtual wave optics
This work shows that the problem of non-line-of-sight imaging can be formulated as one of diffractive wave propagation, by introducing a virtual wave field that is term the phasor field, and yields a new class of imaging algorithms that mimic the capabilities of line- of-sight cameras.
Non-line-of-sight-imaging using dynamic relay surfaces.
This work shows NLOS reconstructions for a relay surface that is non-planar and rapidly changing during data acquisition, and shows that the reconstructions are similar to the ones obtained using a traditional non-dynamic relay surface.
Thermal Non-Line-of-Sight Imaging
A novel non-line-of-sight (NLOS) imaging framework with long-wave infrared (IR) that leverages certain physical parameters more favorable for high-fidelity reconstruction and near real-time and robust NLOS pose estimation of a human figure is proposed.