Prior based Sampling for Adaptive LiDAR
Not on the map. Why?
Abstract (arXiv)
We propose SampleDepth, a Convolutional Neural Network (CNN), that is suited for an adaptive LiDAR. Typically,LiDAR sampling strategy is pre-defined, constant and independent of the observed scene. Instead of letting a LiDAR sample the scene in this agnostic fashion, SampleDepth determines, adaptively, where it is best to sample the current frame. To do that, SampleDepth uses depth samples from previous time steps to predict a sampling mask for the current frame. Crucially, SampleDepth is trained to optimize the performance of a depth completion downstream task. SampleDepth is evaluated on two different depth completion networks and two LiDAR datasets, KITTI Depth Completion and the newly introduced synthetic dataset, SHIFT. We show that SampleDepth is effective and suitable for different depth completion downstream tasks.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 14 Apr 2023.
Builds on
30 of 40 references.
References · 30
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2015Unsupervised Learning of Video Representations using LSTMscited by 434
- 2017Sparsity Invariant CNNscited by 325
- 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
- 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
- 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
- 2022SimVP: Simpler yet Better Video Predictioncited by 181
- 2017Decomposing Motion and Content for Natural Video Sequence Predictioncited by 168
- 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
- 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 149
18 more
- 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
- 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
- 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
- 2018Learning to Decompose and Disentangle Representations for Video Predictioncited by 120
- 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
- 2017Learning to Generate Long-term Future via Hierarchical Predictioncited by 88
- 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
- 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
- 2017Dual Motion GAN for Future-Flow Embedded Video Predictioncited by 69
- 2018SDCNet: Video Prediction Using Spatially-Displaced Convolutioncited by 50
- 2018Propagating Confidences through CNNs for Sparse Data Regressioncited by 36
- 2018Deep Convolutional Compressed Sensing for LiDAR Depth Completioncited by 27
- 2015Learning to Linearize Under Uncertaintycited by 25
- 2020DepthNet: Real-Time LiDAR Point Cloud Depth Completion for Autonomous Vehiclescited by 11
- 2018Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstructioncited by 9
- 2020Adaptive LiDAR Sampling and Depth Completion using Ensemble Variancecited by 8
- 2021SGTBN: Generating Dense Depth Maps from Single-Line LiDARcited by 6
- 2022How to Guide Adaptive Depth Sampling?cited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.