NAVER LABS

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). Project Page: https://jdk9405.github.io/Wid3R/