# Mixed Precision PointPillars for Efficient 3D Object Detection with TensorRT

Source: [Mixed Precision PointPillars for Efficient 3D Object Detection with TensorRT](<https://www.sota2.com/research/paper/69705db5e25ad2fa9d1ed3e0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-04T05:00:15.039Z

Authors: Ninnart Fuengfusin, Keisuke Yoneda, Naoki Suganuma

Published: 2026-01-19T00:59:13.000Z

## Abstract

LIDAR 3D object detection is one of the important tasks for autonomous vehicles. Ensuring that this task operates in real-time is crucial. Toward this, model quantization can be used to accelerate the runtime. However, directly applying model quantization often leads to performance degradation due to LIDAR's wide numerical distributions and extreme outliers. To address the wide numerical distribution, we proposed a mixed precision framework designed for PointPillars. Our framework first searches for sensitive layers with post-training quantization (PTQ) by quantizing one layer at a time to 8-bit integer (INT8) and evaluating each model for average precision (AP). The top-k most sensitive layers are assigned as floating point (FP). Combinations of these layers are greedily searched to produce candidate mixed precision models, which are finalized with either PTQ or quantization-aware training (QAT). Furthermore, to handle outliers, we observe that using a very small number of calibration data reduces the likelihood of encountering outliers, thereby improving PTQ performance. Our methods provides mixed precision models without training in the PTQ pipeline, while our QAT pipeline achieves the performance competitive to FP models. With TensorRT deployment, our mixed precision models offer less latency by up to 2.538 times compared to FP32 models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection on KITTI (AP11 & AP40)](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-ap11-and-ap40.md>): 3D Object Detection; KITTI 3D Object Detection; Car AP11 Easy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.12638>)

[PDF](<https://arxiv.org/pdf/2601.12638.pdf>)