Papers › UniK3D: Universal Camera Monocular 3D Estimation

UniK3D: Universal Camera Monocular 3D Estimation

20 Mar 2025CVPR 2025 1arXiv:2503.16591archive 2025-07-28

Luigi Piccinelli, Christos Sakaridis, Mattia Segu, Yung-Hsu Yang, Siyuan Li, Wim Abbeloos, Luc van Gool

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 .

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lpiccinelli-eth/UniK3D officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D ReconstructionDisentanglementMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split UniK3D (FT, metric) Delta < 1.25 0.990 #2 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniK3D (FT, metric) Delta < 1.25^2 0.998 #2 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniK3D (FT, metric) Delta < 1.25^3 0.999 #2 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniK3D (FT, metric) RMSE 1.68 #2 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniK3D (FT, metric) RMSE log 0.060 #2 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniK3D (FT, metric) absolute relative error 0.037 #2 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniK3D (FT, metric) Delta < 1.25 0.989 #3 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniK3D (FT, metric) Delta < 1.25^2 0.998 #3 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniK3D (FT, metric) Delta < 1.25^3 1.000 #3 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniK3D (FT, metric) RMSE 0.173 #3 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniK3D (FT, metric) absolute relative error 0.044 #3 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniK3D (FT, metric) log 10 0.019 #3 of 85 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections