Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiang, Jijun, Liu, Longliang, Zhu, Xuan, Wang, Xianqi, Lin, Min, Yang, Xin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.26498
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915525678858240
author Xiang, Jijun
Liu, Longliang
Zhu, Xuan
Wang, Xianqi
Lin, Min
Yang, Xin
author_facet Xiang, Jijun
Liu, Longliang
Zhu, Xuan
Wang, Xianqi
Lin, Min
Yang, Xin
contents Depth enhancement, which converts raw dToF signals into dense depth maps using RGB guidance, is crucial for improving depth perception in high-precision tasks such as 3D reconstruction and SLAM. However, existing methods often assume ideal dToF inputs and perfect dToF-RGB alignment, overlooking calibration errors and anomalies, thus limiting real-world applicability. This work systematically analyzes the noise characteristics of real-world lightweight dToF sensors and proposes a practical and novel depth completion framework, DEPTHOR++, which enhances robustness to noisy dToF inputs from three key aspects. First, we introduce a simulation method based on synthetic datasets to generate realistic training samples for robust model training. Second, we propose a learnable-parameter-free anomaly detection mechanism to identify and remove erroneous dToF measurements, preventing misleading propagation during completion. Third, we design a depth completion network tailored to noisy dToF inputs, which integrates RGB images and pre-trained monocular depth estimation priors to improve depth recovery in challenging regions. On the ZJU-L5 dataset and real-world samples, our training strategy significantly boosts existing depth completion models, with our model achieving state-of-the-art performance, improving RMSE and Rel by 22% and 11% on average. On the Mirror3D-NYU dataset, by incorporating the anomaly detection method, our model improves upon the previous SOTA by 37% in mirror regions. On the Hammer dataset, using simulated low-cost dToF data from RealSense L515, our method surpasses the L515 measurements with an average gain of 22%, demonstrating its potential to enable low-cost sensors to outperform higher-end devices. Qualitative results across diverse real-world datasets further validate the effectiveness and generalizability of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance
Xiang, Jijun
Liu, Longliang
Zhu, Xuan
Wang, Xianqi
Lin, Min
Yang, Xin
Computer Vision and Pattern Recognition
Depth enhancement, which converts raw dToF signals into dense depth maps using RGB guidance, is crucial for improving depth perception in high-precision tasks such as 3D reconstruction and SLAM. However, existing methods often assume ideal dToF inputs and perfect dToF-RGB alignment, overlooking calibration errors and anomalies, thus limiting real-world applicability. This work systematically analyzes the noise characteristics of real-world lightweight dToF sensors and proposes a practical and novel depth completion framework, DEPTHOR++, which enhances robustness to noisy dToF inputs from three key aspects. First, we introduce a simulation method based on synthetic datasets to generate realistic training samples for robust model training. Second, we propose a learnable-parameter-free anomaly detection mechanism to identify and remove erroneous dToF measurements, preventing misleading propagation during completion. Third, we design a depth completion network tailored to noisy dToF inputs, which integrates RGB images and pre-trained monocular depth estimation priors to improve depth recovery in challenging regions. On the ZJU-L5 dataset and real-world samples, our training strategy significantly boosts existing depth completion models, with our model achieving state-of-the-art performance, improving RMSE and Rel by 22% and 11% on average. On the Mirror3D-NYU dataset, by incorporating the anomaly detection method, our model improves upon the previous SOTA by 37% in mirror regions. On the Hammer dataset, using simulated low-cost dToF data from RealSense L515, our method surpasses the L515 measurements with an average gain of 22%, demonstrating its potential to enable low-cost sensors to outperform higher-end devices. Qualitative results across diverse real-world datasets further validate the effectiveness and generalizability of our approach.
title DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.26498