Recovering Parametric Scenes from Very Few Time-of-Flight Pixels

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sifferman, Carter, Li, Yiquan, Li, Yiming, Mu, Fangzhou, Gleicher, Michael, Gupta, Mohit, Li, Yin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914047422627840
author Sifferman, Carter
Li, Yiquan
Li, Yiming
Mu, Fangzhou
Gleicher, Michael
Gupta, Mohit
Li, Yin
author_facet Sifferman, Carter
Li, Yiquan
Li, Yiming
Mu, Fangzhou
Gleicher, Michael
Gupta, Mohit
Li, Yin
contents We aim to recover the geometry of 3D parametric scenes using very few depth measurements from low-cost, commercially available time-of-flight sensors. These sensors offer very low spatial resolution (i.e., a single pixel), but image a wide field-of-view per pixel and capture detailed time-of-flight data in the form of time-resolved photon counts. This time-of-flight data encodes rich scene information and thus enables recovery of simple scenes from sparse measurements. We investigate the feasibility of using a distributed set of few measurements (e.g., as few as 15 pixels) to recover the geometry of simple parametric scenes with a strong prior, such as estimating the 6D pose of a known object. To achieve this, we design a method that utilizes both feed-forward prediction to infer scene parameters, and differentiable rendering within an analysis-by-synthesis framework to refine the scene parameter estimate. We develop hardware prototypes and demonstrate that our method effectively recovers object pose given an untextured 3D model in both simulations and controlled real-world captures, and show promising initial results for other parametric scenes. We additionally conduct experiments to explore the limits and capabilities of our imaging solution.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16132
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
Sifferman, Carter
Li, Yiquan
Li, Yiming
Mu, Fangzhou
Gleicher, Michael
Gupta, Mohit
Li, Yin
Computer Vision and Pattern Recognition
We aim to recover the geometry of 3D parametric scenes using very few depth measurements from low-cost, commercially available time-of-flight sensors. These sensors offer very low spatial resolution (i.e., a single pixel), but image a wide field-of-view per pixel and capture detailed time-of-flight data in the form of time-resolved photon counts. This time-of-flight data encodes rich scene information and thus enables recovery of simple scenes from sparse measurements. We investigate the feasibility of using a distributed set of few measurements (e.g., as few as 15 pixels) to recover the geometry of simple parametric scenes with a strong prior, such as estimating the 6D pose of a known object. To achieve this, we design a method that utilizes both feed-forward prediction to infer scene parameters, and differentiable rendering within an analysis-by-synthesis framework to refine the scene parameter estimate. We develop hardware prototypes and demonstrate that our method effectively recovers object pose given an untextured 3D model in both simulations and controlled real-world captures, and show promising initial results for other parametric scenes. We additionally conduct experiments to explore the limits and capabilities of our imaging solution.
title Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.16132