UniK3D: Universal Camera Monocular 3D Estimation
This work solves the problem of poor 3D estimation in real-world scenarios with diverse camera types for applications in visual perception, though it is incremental as it builds on existing monocular 3D estimation methods.
The paper tackles the problem of monocular 3D estimation by addressing limitations of existing methods that rely on simplified camera models, proposing UniK3D, a generalizable method that achieves state-of-the-art performance across 13 diverse datasets, with substantial gains in challenging wide-field-of-view and panoramic settings.
Monocular 3D estimation is crucial for visual perception. However, current methods fall short by relying on oversimplified assumptions, such as pinhole camera models or rectified images. These limitations severely restrict their general applicability, causing poor performance in real-world scenarios with fisheye or panoramic images and resulting in substantial context loss. To address this, we present UniK3D, the first generalizable method for monocular 3D estimation able to model any camera. Our method introduces a spherical 3D representation which allows for better disentanglement of camera and scene geometry and enables accurate metric 3D reconstruction for unconstrained camera models. Our camera component features a novel, model-independent representation of the pencil of rays, achieved through a learned superposition of spherical harmonics. We also introduce an angular loss, which, together with the camera module design, prevents the contraction of the 3D outputs for wide-view cameras. A comprehensive zero-shot evaluation on 13 diverse datasets demonstrates the state-of-the-art performance of UniK3D across 3D, depth, and camera metrics, with substantial gains in challenging large-field-of-view and panoramic settings, while maintaining top accuracy in conventional pinhole small-field-of-view domains. Code and models are available at github.com/lpiccinelli-eth/unik3d .