CAM3R is a camera-agnostic 3D reconstruction model that handles fisheye, panoramic, and pinhole imagery without requiring prior calibration.
March 25, 2026
Original Paper
CAM3R: Camera-Agnostic Model for 3D Reconstruction
arXiv · 2603.22631
The Takeaway
Current 3D reconstruction models are often locked into pinhole geometry, failing on wide-angle or non-rectilinear optics. This model allows for zero-shot 3D geometry and pose estimation from any camera type, dramatically simplifying workflows for AR/VR and mobile robotics.
From the abstract
Recovering dense 3D geometry from unposed images remains a foundational challenge in computer vision. Current state-of-the-art models are predominantly trained on perspective datasets, which implicitly constrains them to a standard pinhole camera geometry. As a result, these models suffer from significant geometric degradation when applied to wide-angle imagery captured via non-rectilinear optics, such as fisheye or panoramic sensors. To address this, we present CAM3R, a Camera-Agnostic, feed-fo