mlsanityData to 7 Oct 2026

FPPN: Future Pseudo-LiDAR Frame Prediction for Autonomous Driving

arXiv 2112.04401 ↗First posted 8 Dec 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

LiDAR sensors are widely used in autonomous driving due to the reliable 3D spatial information. However, the data of LiDAR is sparse and the frequency of LiDAR is lower than that of cameras. To generate denser point clouds spatially and temporally, we propose the first future pseudo-LiDAR frame prediction network. Given the consecutive sparse depth maps and RGB images, we first predict a future dense depth map based on dynamic motion information coarsely. To eliminate the errors of optical flow estimation, an inter-frame aggregation module is proposed to fuse the warped depth maps with adaptive weights. Then, we refine the predicted dense depth map using static contextual information. The future pseudo-LiDAR frame can be obtained by converting the predicted dense depth map into corresponding 3D point clouds. Experimental results show that our method outperforms the existing solutions on the popular KITTI benchmark.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 8 Dec 2021.

Builds on

34 of 44 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  7. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  8. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  9. 2016Generating Videos with Scene Dynamicscited by 376
  10. 2017Sparsity Invariant CNNscited by 325
  11. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  12. 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
22 more
  1. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  2. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 203
  3. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  4. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  5. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  6. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  7. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  8. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  9. 2019ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentationcited by 105
  10. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  11. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  12. 2016An Uncertain Future: Forecasting from Static Images using Variational Autoencoderscited by 86
  13. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  14. 2017Dual Motion GAN for Future-Flow Embedded Video Predictioncited by 69
  15. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  16. 2017Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networkscited by 58
  17. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
  18. 2019FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Datacited by 33
  19. 2020PointINet: Point Cloud Frame Interpolation Networkcited by 12
  20. 2020Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervisioncited by 8
  21. 2020Temporal LiDAR Frame Prediction for Autonomous Drivingcited by 7
  22. 2019PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolationcited by 4

Built on by

Not cited yet.