# Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

arXiv: https://arxiv.org/abs/2307.08209 · HTML: https://mlsanity.com/paper/2307.08209/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 42 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 30 of 35)

- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [Spatially Adaptive Computation Time for Residual Networks](https://mlsanity.com/paper/1612.02297/) (2016)
- [RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection](https://mlsanity.com/paper/2106.13365/) (2021)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)
- [Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2207.10035/) (2022)
- [Channel Gating Neural Networks](https://mlsanity.com/paper/1805.12549/) (2018)
- [TorchSparse: Efficient Point Cloud Inference Engine](https://mlsanity.com/paper/2204.10319/) (2022)
- [Sparse 3D convolutional neural networks](https://mlsanity.com/paper/1505.02890/) (2015)
- [SBNet: Sparse Blocks Network for Fast Inference](https://mlsanity.com/paper/1801.02108/) (2018)
- [Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation](https://mlsanity.com/paper/2003.08866/) (2020)
- [Glance and Focus Networks for Dynamic Visual Recognition](https://mlsanity.com/paper/2201.03014/) (2022)
- [PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection](https://mlsanity.com/paper/2205.11098/) (2022)
- [Super Sparse 3D Object Detection](https://mlsanity.com/paper/2301.02562/) (2023)
- [Spatial Pruned Sparse Convolution for Efficient 3D Object Detection](https://mlsanity.com/paper/2209.14201/) (2022)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)

## Built on by (most cited first, 6 of 6)

- [VALO: A Versatile Anytime Framework for LiDAR-based Object Detection Deep Neural Networks](https://mlsanity.com/paper/2409.11542/) (2024)
- [DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection](https://mlsanity.com/paper/2407.02098/) (2024)
- [A Novel Multi-layer Task-centric and Data Quality Framework for Autonomous Driving](https://mlsanity.com/paper/2506.17346/) (2025)
- [Modeling and Measuring Redundancy in Multisource Multimodal Data for Autonomous Driving](https://mlsanity.com/paper/2603.06544/) (2026)
- [On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection](https://mlsanity.com/paper/2607.08391/) (2026)
- [CARE: Camera-Residual Reserves for First Sightings in Adaptive LiDAR Sensing](https://mlsanity.com/paper/2608.24282/) (2026)

## Abstract (arXiv)

Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles. One reason for this high resource consumption is the presence of a large number of redundant background points in Lidar point clouds, resulting in spatial redundancy in both 3D voxel and dense BEV map representations. To address this issue, we propose an adaptive inference framework called Ada3D, which focuses on exploiting the input-level spatial redundancy. Ada3D adaptively filters the redundant input, guided by a lightweight importance predictor and the unique properties of the Lidar point cloud. Additionally, we utilize the BEV features' intrinsic sparsity by introducing the Sparsity Preserving Batch Normalization. With Ada3D, we achieve 40% reduction for 3D voxels and decrease the density of 2D BEV feature maps from 100% to 20% without sacrificing accuracy. Ada3D reduces the model computational and memory cost by 5x, and achieves 1.52x/1.45x end-to-end GPU latency and 1.5x/4.5x GPU peak memory optimization for the 3D and 2D backbone respectively.