2025-11-10 東京科学大学
図1．従来の複数パターン投影による3次元計測（左）では、運動物体に対して形状誤差が発生していた（中央）。この問題を解決するため、高精度かつ高解像度な形状再構成を実現する手法を提案した（右）。
＜関連情報＞
- https://www.isct.ac.jp/ja/news/frml6m2alks6
- https://openaccess.thecvf.com/content/ICCV2025/html/Urakawa_Neural_Inverse_Rendering_for_High-Accuracy_3D_Measurement_of_Moving_Objects_ICCV_2025_paper.html
位相シフトパターンの少ない移動物体の高精度3D計測を実現するニューラル逆レンダリング Neural Inverse Rendering for High-Accuracy 3D Measurement of Moving Objects with Fewer Phase-Shifting Patterns
Yuki Urakawa, Yoshihiro Watanabe
International Conference on Computer Vision 2025
Abstract
Among structured-light methods, the phase-shifting approach enables high-resolution and high-accuracy measurements using a minimum of three patterns. However, its performance is significantly affected when dynamic and complex-shaped objects are measured, as motion artifacts and phase inconsistencies can degrade accuracy. In this study, we propose an enhanced phase-shifting method that incorporates neural inverse rendering to enable the 3D measurement of moving objects. To effectively capture object motion, we introduce a displacement field into the rendering model, which accurately represents positional changes and mitigates motion-induced distortions. Additionally, to achieve high-precision reconstruction with fewer phase-shifting patterns, we design a multiview-rendering framework that utilizes multiple cameras in conjunction with a single projector. Comparisons with state-of-the-art methods and various ablation studies demonstrated that our method accurately reconstructs the shapes of moving objects, even with a small number of patterns, using only simple, well-known phase-shifting patterns.
