arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05321cs.CV
收藏

Wid3R:通过相机模型条件化实现宽视角三维重建

Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning

University of Maryland, College Park(马里兰大学帕克分校);NAVER LABS

Dongki Jung, Jaehoon Choi, Adil Qureshi, Somi Jeong, Dinesh Manocha, Suyong Yeon

AI总结:

Wid3R是一种多视角视觉几何重建的前馈神经网络,支持宽视角相机模型。该方法通过球谐函数的射线表示和新型相机模型标记实现抗畸变重建,首次支持360影像的多帧前馈3D重建,提升性能达33.67%。

摘要:

我们提出了Wid3R,一种用于多视角视觉几何重建的前馈神经网络,支持宽视角相机模型。不同于现有方法假设校正或针孔输入,Wid3R直接建模宽角图像而无需显式校准或去畸变。我们的方法利用基于射线的表示与球谐函数,并引入新型相机模型标记以实现抗畸变重建。据我们所知,Wid3R是首个支持360影像的多帧前馈3D重建方法。此外,我们表明对多种相机类型进行条件化可提高对360场景的泛化能力并缓解数据稀疏问题。Wid3R在Zip-NeRF(鱼眼)上将AUC@30提升至最高+33.67,在Stanford2D3D(360)上提升至+77.33。

英文摘要:

We present Wid3R, a feed-forward neural network for multi-view visual geometry reconstruction that supports wide field-of-view camera models. Unlike existing methods that assume rectified or pinhole inputs, Wid3R directly models wide-angle imagery without explicit calibration or undistortion. Our approach leverages a ray-based representation with spherical harmonics and introduces a novel camera model token to enable distortion-aware reconstruction. To the best of our knowledge, Wid3R is the first multi-frame feed-forward 3D reconstruction method that supports 360 imagery. Moreover, we show that conditioning on diverse camera types improves generalization to 360 scenes and alleviates data sparsity issues. Wid3R achieves significant performance gains, improving AUC@30 by up to +33.67 on Zip-NeRF (fisheye) and +77.33 on Stanford2D3D (360).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑