# Adaptive LiDAR Sampling and Depth Completion using Ensemble Variance

arXiv: https://arxiv.org/abs/2007.13834 · HTML: https://mlsanity.com/paper/2007.13834/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving](https://mlsanity.com/paper/2405.20337/) (2024)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization](https://mlsanity.com/paper/2201.03860/) (2022)
- [How to Guide Adaptive Depth Sampling?](https://mlsanity.com/paper/2205.10202/) (2022)
- [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)
- [Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization](https://mlsanity.com/paper/2605.15806/) (2026)
- [Passive LWIR Hyperspectral Ranging via Transmittance Extraction and Distance Alignment](https://mlsanity.com/paper/2609.28967/) (2026)

## Abstract (arXiv)

This work considers the problem of depth completion, with or without image data, where an algorithm may measure the depth of a prescribed limited number of pixels. The algorithmic challenge is to choose pixel positions strategically and dynamically to maximally reduce overall depth estimation error. This setting is realized in daytime or nighttime depth completion for autonomous vehicles with a programmable LiDAR. Our method uses an ensemble of predictors to define a sampling probability over pixels. This probability is proportional to the variance of the predictions of ensemble members, thus highlighting pixels that are difficult to predict. By additionally proceeding in several prediction phases, we effectively reduce redundant sampling of similar pixels. Our ensemble-based method may be implemented using any depth-completion learning algorithm, such as a state-of-the-art neural network, treated as a black box. In particular, we also present a simple and effective Random Forest-based algorithm, and similarly use its internal ensemble in our design. We conduct experiments on the KITTI dataset, using the neural network algorithm of Ma et al. and our Random Forest based learner for implementing our method. The accuracy of both implementations exceeds the state of the art. Compared with a random or grid sampling pattern, our method allows a reduction by a factor of 4-10 in the number of measurements required to attain the same accuracy.