Saved in:
Bibliographic Details
Main Authors: Yang, Kai, Bai, Zijian, Xiao, Yang, Li, Xinyu, Shi, Xiaohan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.06125
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908324209885184
author Yang, Kai
Bai, Zijian
Xiao, Yang
Li, Xinyu
Shi, Xiaohan
author_facet Yang, Kai
Bai, Zijian
Xiao, Yang
Li, Xinyu
Shi, Xiaohan
contents 3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique. Previous studies often rely on publicly available datasets for training, focusing on modifying network architectures or incorporating specialized modules to extract domain-invariant features and thus improve model robustness. In contrast, inspired by single-frame structured-light phase-shifting encoding, this study introduces RGB-Speckle, a cross-scene 3D reconstruction framework based on an active stereo camera system, designed to enhance robustness. Specifically, we propose a novel phase pre-normalization encoding-decoding method: first, we randomly perturb phase-shift maps and embed them into the three RGB channels to generate color speckle patterns; subsequently, the camera captures phase-encoded images modulated by objects as input to a stereo matching network. This technique effectively mitigates external interference and ensures consistent input data for RGB-Speckle, thereby bolstering cross-domain 3D reconstruction stability. To validate the proposed method, we conduct complex experiments: (1) construct a color speckle dataset for complex scenarios based on the proposed encoding scheme; (2) evaluate the impact of the phase pre-normalization encoding-decoding technique on 3D reconstruction accuracy; and (3) further investigate its robustness across diverse conditions. Experimental results demonstrate that the proposed RGB-Speckle model offers significant advantages in cross-domain and cross-scene 3D reconstruction tasks, enhancing model generalization and reinforcing robustness in challenging environments, thus providing a novel solution for robust 3D reconstruction research.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization
Yang, Kai
Bai, Zijian
Xiao, Yang
Li, Xinyu
Shi, Xiaohan
Image and Video Processing
Computer Vision and Pattern Recognition
3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique. Previous studies often rely on publicly available datasets for training, focusing on modifying network architectures or incorporating specialized modules to extract domain-invariant features and thus improve model robustness. In contrast, inspired by single-frame structured-light phase-shifting encoding, this study introduces RGB-Speckle, a cross-scene 3D reconstruction framework based on an active stereo camera system, designed to enhance robustness. Specifically, we propose a novel phase pre-normalization encoding-decoding method: first, we randomly perturb phase-shift maps and embed them into the three RGB channels to generate color speckle patterns; subsequently, the camera captures phase-encoded images modulated by objects as input to a stereo matching network. This technique effectively mitigates external interference and ensures consistent input data for RGB-Speckle, thereby bolstering cross-domain 3D reconstruction stability. To validate the proposed method, we conduct complex experiments: (1) construct a color speckle dataset for complex scenarios based on the proposed encoding scheme; (2) evaluate the impact of the phase pre-normalization encoding-decoding technique on 3D reconstruction accuracy; and (3) further investigate its robustness across diverse conditions. Experimental results demonstrate that the proposed RGB-Speckle model offers significant advantages in cross-domain and cross-scene 3D reconstruction tasks, enhancing model generalization and reinforcing robustness in challenging environments, thus providing a novel solution for robust 3D reconstruction research.
title RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06125