# Been There, Scanned That: Nostalgia-Driven LiDAR Compression for Self-Driving Cars

arXiv: https://arxiv.org/abs/2511.00652 · HTML: https://mlsanity.com/paper/2511.00652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving.
- Builds on 22 of its 72 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Placed in

- End-to-end autonomous driving / [End-to-end system architecture](https://mlsanity.com/driving/end-to-end-system-architecture/)

## Builds on (most cited first, 22 of 22)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [FAST-LIO2: Fast Direct LiDAR-inertial Odometry](https://mlsanity.com/paper/2107.06829/) (2021)
- [FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter](https://mlsanity.com/paper/2010.08196/) (2020)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression](https://mlsanity.com/paper/2005.07178/) (2020)
- [VoxelContext-Net: An Octree based Framework for Point Cloud Compression](https://mlsanity.com/paper/2105.02158/) (2021)
- [Learned Point Cloud Geometry Compression](https://mlsanity.com/paper/1909.12037/) (2019)
- [Improving Deep Video Compression by Resolution-adaptive Flow Coding](https://mlsanity.com/paper/2009.05982/) (2020)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression](https://mlsanity.com/paper/1903.08548/) (2019)
- [Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds](https://mlsanity.com/paper/1905.03691/) (2019)
- [RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding](https://mlsanity.com/paper/2206.01738/) (2022)
- [Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution](https://mlsanity.com/paper/1811.09361/) (2018)
- [Real-Time Spatio-Temporal LiDAR Point Cloud Compression](https://mlsanity.com/paper/2008.06972/) (2020)
- [RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2503.12382/) (2025)
- [I2VC: A Unified Framework for Intra- & Inter-frame Video Compression](https://mlsanity.com/paper/2405.14336/) (2024)
- [Long-term map maintenance pipeline for autonomous vehicles](https://mlsanity.com/paper/2008.12449/) (2020)

## Abstract (arXiv)

An autonomous vehicle can generate several terabytes of sensor data per day. A significant portion of this data consists of 3D point clouds produced by depth sensors such as LiDARs. This data must be transferred to cloud storage, where it is utilized for training machine learning models or conducting analyses, such as forensic investigations in the event of an accident. To reduce network and storage costs, this paper introduces DejaView. Although prior work uses interframe redundancies to compress data, DejaView searches for and uses redundancies on larger temporal scales (days and months) for more effective compression. We designed DejaView with the insight that the operating area of autonomous vehicles is limited and that vehicles mostly traverse the same routes daily. Consequently, the 3D data they collect daily is likely similar to the data they have captured in the past. To capture this, the core of DejaView is a diff operation that compactly represents point clouds as delta w.r.t. 3D data from the past. Using two months of LiDAR data, an end-to-end implementation of DejaView can compress point clouds by a factor of 210 at a reconstruction error of only 15 cm.