# CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

arXiv: https://arxiv.org/abs/1904.02028 · HTML: https://mlsanity.com/paper/1904.02028/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 30 of 75)

- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler](https://mlsanity.com/paper/2502.20110/) (2025)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [Rethinking Inductive Biases for Surface Normal Estimation](https://mlsanity.com/paper/2403.00712/) (2024)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Towards Zero-Shot Scale-Aware Monocular Depth Estimation](https://mlsanity.com/paper/2306.17253/) (2023)
- [Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot](https://mlsanity.com/paper/2402.14654/) (2024)
- [Geometry-based Distance Decomposition for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.03775/) (2021)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints](https://mlsanity.com/paper/2103.16525/) (2021)
- [PromptHMR: Promptable Human Mesh Recovery](https://mlsanity.com/paper/2504.06397/) (2025)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving](https://mlsanity.com/paper/2102.07448/) (2021)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [3D Hand Pose Estimation in Everyday Egocentric Images](https://mlsanity.com/paper/2312.06583/) (2023)
- [PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss](https://mlsanity.com/paper/2103.07362/) (2021)
- [Input-level Inductive Biases for 3D Reconstruction](https://mlsanity.com/paper/2112.03243/) (2021)
- [Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model](https://mlsanity.com/paper/2312.13252/) (2023)
- [Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2303.01686/) (2023)
- [SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras](https://mlsanity.com/paper/2104.04420/) (2021)
- [Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image](https://mlsanity.com/paper/2110.05655/) (2021)
- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)
- [AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration](https://mlsanity.com/paper/2503.12701/) (2025)
- [LightDepth: Single-View Depth Self-Supervision from Illumination Decline](https://mlsanity.com/paper/2308.10525/) (2023)
- [SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens](https://mlsanity.com/paper/2411.19824/) (2024)
- [Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation](https://mlsanity.com/paper/2109.11798/) (2021)
- [G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data](https://mlsanity.com/paper/2310.15422/) (2023)

## Abstract (arXiv)

Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras.