Photoreal Scene Reconstruction from an Egocentric Device

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lv, Zhaoyang, Monge, Maurizio, Chen, Ka, Zhu, Yufeng, Goesele, Michael, Engel, Jakob, Dong, Zhao, Newcombe, Richard
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909638799130624
author Lv, Zhaoyang
Monge, Maurizio
Chen, Ka
Zhu, Yufeng
Goesele, Michael
Engel, Jakob
Dong, Zhao
Newcombe, Richard
author_facet Lv, Zhaoyang
Monge, Maurizio
Chen, Ka
Zhu, Yufeng
Goesele, Michael
Engel, Jakob
Dong, Zhao
Newcombe, Richard
contents In this paper, we investigate the challenges associated with using egocentric devices to photorealistic reconstruct the scene in high dynamic range. Existing methodologies typically assume using frame-rate 6DoF pose estimated from the device's visual-inertial odometry system, which may neglect crucial details necessary for pixel-accurate reconstruction. This study presents two significant findings. Firstly, in contrast to mainstream work treating RGB camera as global shutter frame-rate camera, we emphasize the importance of employing visual-inertial bundle adjustment (VIBA) to calibrate the precise timestamps and movement of the rolling shutter RGB sensing camera in a high frequency trajectory format, which ensures an accurate calibration of the physical properties of the rolling-shutter camera. Secondly, we incorporate a physical image formation model based into Gaussian Splatting, which effectively addresses the sensor characteristics, including the rolling-shutter effect of RGB cameras and the dynamic ranges measured by sensors. Our proposed formulation is applicable to the widely-used variants of Gaussian Splats representation. We conduct a comprehensive evaluation of our pipeline using the open-source Project Aria device under diverse indoor and outdoor lighting conditions, and further validate it on a Meta Quest3 device. Across all experiments, we observe a consistent visual enhancement of +1 dB in PSNR by incorporating VIBA, with an additional +1 dB achieved through our proposed image formation model. Our complete implementation, evaluation datasets, and recording profile are available at http://www.projectaria.com/photoreal-reconstruction/
format Preprint
id arxiv_https___arxiv_org_abs_2506_04444
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Photoreal Scene Reconstruction from an Egocentric Device
Lv, Zhaoyang
Monge, Maurizio
Chen, Ka
Zhu, Yufeng
Goesele, Michael
Engel, Jakob
Dong, Zhao
Newcombe, Richard
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Human-Computer Interaction
Multimedia
In this paper, we investigate the challenges associated with using egocentric devices to photorealistic reconstruct the scene in high dynamic range. Existing methodologies typically assume using frame-rate 6DoF pose estimated from the device's visual-inertial odometry system, which may neglect crucial details necessary for pixel-accurate reconstruction. This study presents two significant findings. Firstly, in contrast to mainstream work treating RGB camera as global shutter frame-rate camera, we emphasize the importance of employing visual-inertial bundle adjustment (VIBA) to calibrate the precise timestamps and movement of the rolling shutter RGB sensing camera in a high frequency trajectory format, which ensures an accurate calibration of the physical properties of the rolling-shutter camera. Secondly, we incorporate a physical image formation model based into Gaussian Splatting, which effectively addresses the sensor characteristics, including the rolling-shutter effect of RGB cameras and the dynamic ranges measured by sensors. Our proposed formulation is applicable to the widely-used variants of Gaussian Splats representation. We conduct a comprehensive evaluation of our pipeline using the open-source Project Aria device under diverse indoor and outdoor lighting conditions, and further validate it on a Meta Quest3 device. Across all experiments, we observe a consistent visual enhancement of +1 dB in PSNR by incorporating VIBA, with an additional +1 dB achieved through our proposed image formation model. Our complete implementation, evaluation datasets, and recording profile are available at http://www.projectaria.com/photoreal-reconstruction/
title Photoreal Scene Reconstruction from an Egocentric Device
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Human-Computer Interaction
Multimedia
url https://arxiv.org/abs/2506.04444