All-day Depth Completion

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ezhov, Vadim, Park, Hyoungseob, Zhang, Zhaoyang, Upadhyay, Rishi, Zhang, Howard, Chandrappa, Chethan Chinder, Kadambi, Achuta, Ba, Yunhao, Dorsey, Julie, Wong, Alex
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914813822631936
author Ezhov, Vadim
Park, Hyoungseob
Zhang, Zhaoyang
Upadhyay, Rishi
Zhang, Howard
Chandrappa, Chethan Chinder
Kadambi, Achuta
Ba, Yunhao
Dorsey, Julie
Wong, Alex
author_facet Ezhov, Vadim
Park, Hyoungseob
Zhang, Zhaoyang
Upadhyay, Rishi
Zhang, Howard
Chandrappa, Chethan Chinder
Kadambi, Achuta
Ba, Yunhao
Dorsey, Julie
Wong, Alex
contents We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty - we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities - depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 25% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 11.65% in all-day scenarios, 11.23% when tested specifically for daytime, and 13.12% for nighttime scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle All-day Depth Completion
Ezhov, Vadim
Park, Hyoungseob
Zhang, Zhaoyang
Upadhyay, Rishi
Zhang, Howard
Chandrappa, Chethan Chinder
Kadambi, Achuta
Ba, Yunhao
Dorsey, Julie
Wong, Alex
Computer Vision and Pattern Recognition
We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty - we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities - depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 25% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 11.65% in all-day scenarios, 11.23% when tested specifically for daytime, and 13.12% for nighttime scenes.
title All-day Depth Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.17315