Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses

ArXi:2603.28896v1 Announce Type: new Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view images, e.g., from a fisheye camera, their performance degrades. Their error arises from changes in spatial positions of pixels due to a non-linear projection model that maps 3D points onto the 2D image plane. While one may surmise that