**Are you an EPFL student looking for a semester project?**

Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.

Publication# Learned Compressive Representations for Single-Photon 3D Imaging

Abstract

Single-photon 3D cameras can record the time-of-arrival of billions of photons per second with picosecond accuracy. One common approach to summarize the photon data stream is to build a per-pixel timestamp histogram, resulting in a 3D histogram tensor that encodes distances along the time axis. As the spatio-temporal resolution of the histogram tensor increases, the in-pixel memory requirements and output data rates can quickly become impractical. To overcome this limitation, we propose a family of linear compressive representations of histogram tensors that can be computed efficiently, in an online fashion, as a matrix operation. We design practical lightweight compressive representations that are amenable to an in-pixel implementation and consider the spatio-temporal information of each timestamp. Furthermore, we implement our proposed framework as the first layer of a neural network, which enables the joint end-to-end optimization of the compressive representations and a downstream SPAD data processing model. We find that a well-designed compressive representation can reduce in-sensor memory and data rates up to 2 orders of magnitude without significantly reducing 3D imaging quality. Finally, we analyze the power consumption implications through an on-chip implementation.

Official source

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts (34)

Ontological neighbourhood

Related publications (33)

Related MOOCs (20)

Structure tensor

In mathematics, the structure tensor, also referred to as the second-moment matrix, is a matrix derived from the gradient of a function. It describes the distribution of the gradient in a specified neighborhood around a point and makes the information invariant respect the observing coordinates. The structure tensor is often used in and computer vision. For a function of two variables p = (x, y), the structure tensor is the 2×2 matrix where and are the partial derivatives of with respect to x and y; the integrals range over the plane ; and w is some fixed "window function" (such as a Gaussian blur), a distribution on two variables.

Scale-invariant feature transform

The scale-invariant feature transform (SIFT) is a computer vision algorithm to detect, describe, and match local features in images, invented by David Lowe in 1999. Applications include object recognition, robotic mapping and navigation, , 3D modeling, gesture recognition, video tracking, individual identification of wildlife and match moving. SIFT keypoints of objects are first extracted from a set of reference images and stored in a database.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Algebra (part 1)

Un MOOC francophone d'algèbre linéaire accessible à tous, enseigné de manière rigoureuse et ne nécessitant aucun prérequis.

Algebra (part 1)

Un MOOC francophone d'algèbre linéaire accessible à tous, enseigné de manière rigoureuse et ne nécessitant aucun prérequis.

Algebra (part 2)

Un MOOC francophone d'algèbre linéaire accessible à tous, enseigné de manière rigoureuse et ne nécessitant aucun prérequis.

Joshua Alexander Harrison Klein

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

Vision systems built around conventional image sensors have to read, encode and transmit large quantities of pixel information, a majority of which is redundant. As a result, new computational imaging sensor architectures were developed to preprocess the r ...

Nicolas Henri Bernard Flammarion, Etienne Patrice Boursier

Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between parameters' norm and obtained estimators theoretically remains misunderstood. For one hidden ReLU layer networks ...

2023