Towards Cross-Platform Generalization: Domain Adaptive 3D Detection with Augmentation and Pseudo-Labeling

TL;DR

This paper presents a domain adaptive 3D detection method that combines data augmentation and pseudo-labeling to improve cross-platform generalization, achieving top challenge results.

Contribution

It introduces a novel approach building on PVRCNN++ with tailored augmentation and self-training for better domain adaptation in 3D detection.

Findings

Achieved 3D AP of 62.67% for cars on target domain

Secured 3rd place in RoboSense2025 Challenge

Effective domain gap reduction through augmentation and pseudo-labeling

Abstract

This technical report represents the award-winning solution to the Cross-platform 3D Object Detection task in the RoboSense2025 Challenge. Our approach is built upon PVRCNN++, an efficient 3D object detection framework that effectively integrates point-based and voxel-based features. On top of this foundation, we improve cross-platform generalization by narrowing domain gaps through tailored data augmentation and a self-training strategy with pseudo-labels. These enhancements enabled our approach to secure the 3rd place in the challenge, achieving a 3D AP of 62.67% for the Car category on the phase-1 target domain, and 58.76% and 49.81% for Car and Pedestrian categories respectively on the phase-2 target domain.