Mixed Precision l1 Solver for Compressive Depth Reconstruction: An ADMM Case Study

Yun Wu; Andrew Michael Wallace; Andreas Aßmann; Brian Stewart

Mixed Precision l1 Solver for Compressive Depth Reconstruction: An ADMM Case Study

Yun Wu, Andrew Michael Wallace, Andreas Aßmann, Brian Stewart

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

74 Downloads (Pure)

Abstract

Rapid reconstruction of depth images from sparsely sampled data is important for many machine learning applications, including robot or vehicle assistance or autonomy, which require low power LiDAR sensing for eye safety, and resource reduction for FPGA or solid state implementation, especially with constrained energy budgets. A new compressive depth reconstruction design approach is proposed using a compact ADMM solver for the lasso problem, which varies the precision scaling in an iterative optimization process. Implementations on an FPGA architecture show over 55% savings in hardware resources and 78% in power with only minor reduction in reconstructed depth image quality compared to single float precision.

Original language	English
Title of host publication	2021 International Workshop on Signal Processing Systems
Publication status	Accepted/In press - 5 Jul 2021
Event	2021 International Workshop on Signal Processing Systems - Coimbra, Portugal Duration: 19 Oct 2021 → 21 Oct 2021 https://sips2021.org/

Workshop

Workshop	2021 International Workshop on Signal Processing Systems
Abbreviated title	SiPS 2021
Country/Territory	Portugal
City	Coimbra
Period	19/10/21 → 21/10/21
Internet address	https://sips2021.org/

Access to Document

Download pdf
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.16 MB

Cite this

@inproceedings{be98689fd70943589387fec3c19df441,

title = "Mixed Precision l1 Solver for Compressive Depth Reconstruction: An ADMM Case Study",

abstract = "Rapid reconstruction of depth images from sparsely sampled data is important for many machine learning applications, including robot or vehicle assistance or autonomy, which require low power LiDAR sensing for eye safety, and resource reduction for FPGA or solid state implementation, especially with constrained energy budgets. A new compressive depth reconstruction design approach is proposed using a compact ADMM solver for the lasso problem, which varies the precision scaling in an iterative optimization process. Implementations on an FPGA architecture show over 55% savings in hardware resources and 78% in power with only minor reduction in reconstructed depth image quality compared to single float precision.",

author = "Yun Wu and Wallace, {Andrew Michael} and Andreas A{\ss}mann and Brian Stewart",

year = "2021",

month = jul,

day = "5",

language = "English",

booktitle = "2021 International Workshop on Signal Processing Systems",

note = "2021 International Workshop on Signal Processing Systems, SiPS 2021 ; Conference date: 19-10-2021 Through 21-10-2021",

url = "https://sips2021.org/",

}

TY - GEN

T1 - Mixed Precision l1 Solver for Compressive Depth Reconstruction: An ADMM Case Study

AU - Wu, Yun

AU - Wallace, Andrew Michael

AU - Aßmann, Andreas

AU - Stewart, Brian

PY - 2021/7/5

Y1 - 2021/7/5

N2 - Rapid reconstruction of depth images from sparsely sampled data is important for many machine learning applications, including robot or vehicle assistance or autonomy, which require low power LiDAR sensing for eye safety, and resource reduction for FPGA or solid state implementation, especially with constrained energy budgets. A new compressive depth reconstruction design approach is proposed using a compact ADMM solver for the lasso problem, which varies the precision scaling in an iterative optimization process. Implementations on an FPGA architecture show over 55% savings in hardware resources and 78% in power with only minor reduction in reconstructed depth image quality compared to single float precision.

AB - Rapid reconstruction of depth images from sparsely sampled data is important for many machine learning applications, including robot or vehicle assistance or autonomy, which require low power LiDAR sensing for eye safety, and resource reduction for FPGA or solid state implementation, especially with constrained energy budgets. A new compressive depth reconstruction design approach is proposed using a compact ADMM solver for the lasso problem, which varies the precision scaling in an iterative optimization process. Implementations on an FPGA architecture show over 55% savings in hardware resources and 78% in power with only minor reduction in reconstructed depth image quality compared to single float precision.

M3 - Conference contribution

BT - 2021 International Workshop on Signal Processing Systems

T2 - 2021 International Workshop on Signal Processing Systems

Y2 - 19 October 2021 through 21 October 2021

ER -

Mixed Precision l1 Solver for Compressive Depth Reconstruction: An ADMM Case Study

Abstract

Workshop

Access to Document

Fingerprint

Cite this