Holographic near-eye displays offer unprecedented capabilities for virtual and augmented reality systems, including perceptually important focus cues.
Neural networks can represent and accurately reconstruct radiance fields for static 3D scenes (e. g., NeRF).
LiDAR sensors can be used to obtain a wide range of measurement signals other than a simple 3D point cloud, and those signals can be leveraged to improve perception tasks like 3D object detection.
Non-line-of-sight (NLOS) imaging techniques use light that diffusely reflects off of visible surfaces (e. g., walls) to see around corners.
We bring together a diverse set of technologies from NLOS imaging, human pose estimation and deep reinforcement learning to construct an end-to-end data processing pipeline that converts a raw stream of photon measurements into a full 3D human pose sequence estimate.
However, when imaging multiple NLOS objects, the speckle components due to different objects are superimposed on the virtual bare sensor image, and cannot be analyzed separately for recovering the motion of individual objects.
Imaging objects obscured by occluders is a significant challenge for many applications.
Computer vision algorithms build on 2D images or 3D videos that capture dynamic events at the millisecond time scale.
Continuous-wave time-of-flight (ToF) cameras show great promise as low-cost depth image sensors in mobile applications.
We consider the problem of deliberately manipulating the direct and indirect light flowing through a time-varying, fully-general scene in order to simplify its visual analysis.