# How to Guide Adaptive Depth Sampling?

arXiv: https://arxiv.org/abs/2205.10202 · HTML: https://mlsanity.com/paper/2205.10202/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 30 of 32)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image](https://mlsanity.com/paper/1709.07492/) (2017)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018)
- [Learning Guided Convolutional Network for Depth Completion](https://mlsanity.com/paper/1908.01238/) (2019)
- [Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1808.00150/) (2018)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [Semantic Image Synthesis via Adversarial Learning](https://mlsanity.com/paper/1707.06873/) (2017)
- [Sparse and noisy LiDAR completion with RGB guidance and uncertainty](https://mlsanity.com/paper/1902.05356/) (2019)
- [Scribbler: Controlling Deep Image Synthesis with Sketch and Color](https://mlsanity.com/paper/1612.00835/) (2016)
- [SampleNet: Differentiable Point Cloud Sampling](https://mlsanity.com/paper/1912.03663/) (2019)
- [Learning Joint 2D-3D Representations for Depth Completion](https://mlsanity.com/paper/2012.12402/) (2020)
- [Confidence Propagation through CNNs for Guided Sparse Depth Regression](https://mlsanity.com/paper/1811.01791/) (2018)
- [Generative Image Modeling using Style and Structure Adversarial Networks](https://mlsanity.com/paper/1603.05631/) (2016)
- [DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion](https://mlsanity.com/paper/1902.00761/) (2019)
- [Time-Travel Rephotography](https://mlsanity.com/paper/2012.12261/) (2020)
- [Estimating Depth from RGB and Sparse Sensing](https://mlsanity.com/paper/1804.02771/) (2018)
- [Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts](https://mlsanity.com/paper/1612.00215/) (2016)

## Built on by (most cited first, 2 of 2)

- [Prior based Sampling for Adaptive LiDAR](https://mlsanity.com/paper/2304.07099/) (2023)
- [Progressive Depth Decoupling and Modulating for Flexible Depth Completion](https://mlsanity.com/paper/2405.09342/) (2024)

## Abstract (arXiv)

Recent advances in depth sensing technologies allow fast electronic maneuvering of the laser beam, as opposed to fixed mechanical rotations. This will enable future sensors, in principle, to vary in real-time the sampling pattern. We examine here the abstract problem of whether adapting the sampling pattern for a given frame can reduce the reconstruction error or allow a sparser pattern. We propose a constructive generic method to guide adaptive depth sampling algorithms. Given a sampling budget B, a depth predictor P and a desired quality measure M, we propose an Importance Map that highlights important sampling locations. This map is defined for a given frame as the per-pixel expected value of M produced by the predictor P, given a pattern of B random samples. This map can be well estimated in a training phase. We show that a neural network can learn to produce a highly faithful Importance Map, given an RGB image. We then suggest an algorithm to produce a sampling pattern for the scene, which is denser in regions that are harder to reconstruct. The sampling strategy of our modular framework can be adjusted according to hardware limitations, type of depth predictor, and any custom reconstruction error measure that should be minimized. We validate through simulations that our approach outperforms grid and random sampling patterns as well as recent state-of-the-art adaptive algorithms.