CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ding, Laiyan, Jiang, Hualie, Xu, Rui, Huang, Rui
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913595232616448
author Ding, Laiyan
Jiang, Hualie
Xu, Rui
Huang, Rui
author_facet Ding, Laiyan
Jiang, Hualie
Xu, Rui
Huang, Rui
contents Depth completion using lightweight time-of-flight (ToF) depth sensors is attractive due to their low cost. However, lightweight ToF sensors usually have a limited field of view (FOV) compared with cameras. Thus, only pixels in the zone area of the image can be associated with depth signals. Previous methods fail to propagate depth features from the zone area to the outside-zone area effectively, thus suffering from degraded depth completion performance outside the zone. To this end, this paper proposes the CFPNet to achieve cross-zone feature propagation from the zone area to the outside-zone area with two novel modules. The first is a direct-attention-based propagation module (DAPM), which enforces direct cross-zone feature acquisition. The second is a large-kernel-based propagation module (LKPM), which realizes cross-zone feature propagation by utilizing convolution layers with kernel sizes up to 31. CFPNet achieves state-of-the-art (SOTA) depth completion performance by combining these two modules properly, as verified by extensive experimental results on the ZJU-L5 dataset. The code is available at https://github.com/denyingmxd/CFPNet.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04480
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation
Ding, Laiyan
Jiang, Hualie
Xu, Rui
Huang, Rui
Computer Vision and Pattern Recognition
Depth completion using lightweight time-of-flight (ToF) depth sensors is attractive due to their low cost. However, lightweight ToF sensors usually have a limited field of view (FOV) compared with cameras. Thus, only pixels in the zone area of the image can be associated with depth signals. Previous methods fail to propagate depth features from the zone area to the outside-zone area effectively, thus suffering from degraded depth completion performance outside the zone. To this end, this paper proposes the CFPNet to achieve cross-zone feature propagation from the zone area to the outside-zone area with two novel modules. The first is a direct-attention-based propagation module (DAPM), which enforces direct cross-zone feature acquisition. The second is a large-kernel-based propagation module (LKPM), which realizes cross-zone feature propagation by utilizing convolution layers with kernel sizes up to 31. CFPNet achieves state-of-the-art (SOTA) depth completion performance by combining these two modules properly, as verified by extensive experimental results on the ZJU-L5 dataset. The code is available at https://github.com/denyingmxd/CFPNet.
title CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.04480