UniDAC: Universal Metric Depth Estimation for Any Camera

• URL: http://arxiv.org/abs/2603.27105v1
• Date: Sat, 28 Mar 2026 03:23:08 GMT
• Title: UniDAC: Universal Metric Depth Estimation for Any Camera
• Abstract summary: Monocular metric depth estimation (MMDE) is a core challenge in computer vision, playing a pivotal role in real-world applications that demand accurate spatial understanding.<n>We propose UniDAC, an MMDE framework that presents universal robustness in all domains and generalizes across diverse cameras using a single model.<n>We achieve this by decoupling metric depth estimation into relative depth prediction and spatially varying scale estimation, enabling robust performance across different domains.
• Score: 27.152509271066098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular metric depth estimation (MMDE) is a core challenge in computer vision, playing a pivotal role in real-world applications that demand accurate spatial understanding. Although prior works have shown promising zero-shot performance in MMDE, they often struggle with generalization across diverse camera types, such as fisheye and $360^\circ$ cameras. Recent advances have addressed this through unified camera representations or canonical representation spaces, but they require either including large-FoV camera data during training or separately trained models for different domains. We propose UniDAC, an MMDE framework that presents universal robustness in all domains and generalizes across diverse cameras using a single model. We achieve this by decoupling metric depth estimation into relative depth prediction and spatially varying scale estimation, enabling robust performance across different domains. We propose a lightweight Depth-Guided Scale Estimation module that upsamples a coarse scale map to high resolution using the relative depth map as guidance to account for local scale variations. Furthermore, we introduce RoPE-$φ$, a distortion-aware positional embedding that respects the spatial warping in Equi-Rectangular Projections (ERP) via latitude-aware weighting. UniDAC achieves state of the art (SoTA) in cross-camera generalization by consistently outperforming prior methods across all datasets.

Related papers

• OmniPoint: Universal Monocular Metric Pointcloud from Any Camera [79.24417597712802]
  We present OmniPoint, a unified framework designed to generalize metric reconstruction across diverse imaging sensors.<n>To overcome projection rigidity, OmniPoint abandons conventional planar depth regression.<n>It instead adopts a decoupled ray and distance representation alongside a decoupled training objective.
  arXiv  Detail & Related papers  (2026-09-08T19:45:58Z)
• Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving [21.827292830060728]
  Semi-SMD is a novel metric depth estimation framework tailored for surrounding cameras equipment in autonomous driving.<n>We propose a unified spatial-temporal-semantic fusion module to construct the visual fused features.<n>We evaluate our algorithm on DDAD and nuScenes datasets, and the results demonstrate that our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-25T14:39:04Z)
• UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler [62.06785782635153]
  We propose a new model, UniDepthV2, capable of reconstructing metric 3D scenes from solely single images across domains.<n>UniDepthV2 directly predicts metric 3D points from the input image at inference time without any additional information.<n>Our model exploits a pseudo-spherical output representation, which disentangles the camera and depth representations.
  arXiv  Detail & Related papers  (2025-02-27T14:03:15Z)
• Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera [13.459760768067216]
  This paper presents Depth Any Camera (DAC), a powerful zero-shot metric depth estimation framework.<n>The framework is designed to ensure that all existing 3D data can be leveraged, regardless of the specific camera types used in new applications.
  arXiv  Detail & Related papers  (2025-01-05T07:22:40Z)
• GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion [0.0]
  Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature.<n>We propose a novel canonical representation that maintains consistency across varied camera setups.<n>We also propose a novel architecture that adaptively and probabilistically fuses depths estimated via object size and vertical image position cues.
  arXiv  Detail & Related papers  (2024-12-08T22:04:34Z)
• UniDepth: Universal Monocular Metric Depth Estimation [81.80512457953903]
  We propose a new model, UniDepth, capable of reconstructing metric 3D scenes from solely single images across domains. Our model exploits a pseudo-spherical output representation, which disentangles camera and depth representations. Thorough evaluations on ten datasets in a zero-shot regime consistently demonstrate the superior performance of UniDepth.
  arXiv  Detail & Related papers  (2024-03-27T18:06:31Z)
• FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization [57.98448472585241]
  We propose a method to train a stereo depth estimation model on the widely available pinhole data. We show strong generalization ability of our approach on both indoor and outdoor datasets.
  arXiv  Detail & Related papers  (2024-01-24T20:07:59Z)
• GEDepth: Ground Embedding for Monocular Depth Estimation [4.95394574147086]
  This paper proposes a novel ground embedding module to decouple camera parameters from pictorial cues. A ground attention is designed in the module to optimally combine ground depth with residual depth. Experiments reveal that our approach achieves the state-of-the-art results on popular benchmarks.
  arXiv  Detail & Related papers  (2023-09-18T17:56:06Z)
• Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation [75.99435808648784]
  We propose a novel multi-camera collaborative depth prediction method. It does not require large overlapping areas while maintaining structure consistency between cameras. Experimental results on DDAD and NuScenes datasets demonstrate the superior performance of our method.
  arXiv  Detail & Related papers  (2022-10-05T03:44:34Z)
• Towards Model Generalization for Monocular 3D Object Detection [57.25828870799331]
  We present an effective unified camera-generalized paradigm (CGP) for Mono3D object detection. We also propose the 2D-3D geometry-consistent object scaling strategy (GCOS) to bridge the gap via an instance-level augment. Our method called DGMono3D achieves remarkable performance on all evaluated datasets and surpasses the SoTA unsupervised domain adaptation scheme.
  arXiv  Detail & Related papers  (2022-05-23T23:05:07Z)
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation [101.55622133406446]
  We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets.
  arXiv  Detail & Related papers  (2022-04-07T17:58:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.