# UniK3D: Universal Camera Monocular 3D Estimation

arXiv: https://arxiv.org/abs/2503.16591 · HTML: https://mlsanity.com/paper/2503.16591/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 92 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 30 of 70)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)

## Built on by (most cited first, 30 of 62)

- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels](https://mlsanity.com/paper/2507.21809/) (2025)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [DA2: Depth Anything in Any Direction](https://mlsanity.com/paper/2509.26618/) (2025)
- [Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation](https://mlsanity.com/paper/2512.16913/) (2025)
- [EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark](https://mlsanity.com/paper/2510.06218/) (2025)
- [PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery](https://mlsanity.com/paper/2603.17571/) (2026)
- [3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection](https://mlsanity.com/paper/2507.23567/) (2025)
- [Loc2: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching](https://mlsanity.com/paper/2509.09792/) (2025)
- [UniDAC: Universal Metric Depth Estimation for Any Camera](https://mlsanity.com/paper/2603.27105/) (2026)
- [MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement](https://mlsanity.com/paper/2607.17967/) (2026)
- [Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses](https://mlsanity.com/paper/2603.28896/) (2026)
- [Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning](https://mlsanity.com/paper/2602.05321/) (2026)
- [CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation](https://mlsanity.com/paper/2605.12938/) (2026)
- [Video Depth Propagation](https://mlsanity.com/paper/2512.10725/) (2025)
- [Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates](https://mlsanity.com/paper/2602.18906/) (2026)
- [X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras](https://mlsanity.com/paper/2607.12993/) (2026)
- [Depth Anything in 360^circ: Towards Scale Invariance in the Wild](https://mlsanity.com/paper/2512.22819/) (2025)
- [Fly360: Omnidirectional Obstacle Avoidance within Drone View](https://mlsanity.com/paper/2603.06573/) (2026)
- [AURORA-KITTI: Any-Weather Depth Completion and Denoising](https://mlsanity.com/paper/2603.14701/) (2026)
- [CAM3R: Camera-Agnostic Model for 3D Reconstruction](https://mlsanity.com/paper/2603.22631/) (2026)
- [UniSHARP: Universal Sharp Monocular View Synthesis](https://mlsanity.com/paper/2606.07514/) (2026)
- [TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrast](https://mlsanity.com/paper/2506.13387/) (2025)
- [ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving](https://mlsanity.com/paper/2508.13977/) (2025)
- [CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis](https://mlsanity.com/paper/2603.05882/) (2026)
- [GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes](https://mlsanity.com/paper/2603.17993/) (2026)
- [DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection](https://mlsanity.com/paper/2605.23281/) (2026)
- [WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation](https://mlsanity.com/paper/2605.24074/) (2026)
- [Unified Panoramic Geometry Estimation via Multi-View Foundation Models](https://mlsanity.com/paper/2605.26368/) (2026)
- [Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling](https://mlsanity.com/paper/2606.27745/) (2026)

## Abstract (arXiv)

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 .