NIGHT -- Non-Line-of-Sight Imaging from Indirect Time of Flight Data
This enables non-line-of-sight imaging without custom hardware, potentially benefiting surveillance or robotics, but it is incremental as it adapts existing concepts to a new sensor type.
The paper tackled non-line-of-sight imaging using only an off-the-shelf indirect Time of Flight sensor, introducing a deep learning model that reframes light bounce surfaces as virtual mirrors to retrieve depth information of hidden scenes, demonstrating feasibility on a synthetic dataset.
The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic. Recent works showed the feasibility of this idea exploiting transient imaging data produced by custom direct Time of Flight sensors. In this paper, for the first time, we tackle this problem using only data from an off-the-shelf indirect Time of Flight sensor without any further hardware requirement. We introduced a Deep Learning model able to re-frame the surfaces where light bounces happen as a virtual mirror. This modeling makes the task easier to handle and also facilitates the construction of annotated training data. From the obtained data it is possible to retrieve the depth information of the hidden scene. We also provide a first-in-its-kind synthetic dataset for the task and demonstrate the feasibility of the proposed idea over it.