Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation
This addresses a key challenge for autonomous vehicles and robots operating in unstructured environments, though it appears incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of performance drop in 3D object recognition when using sparse point clouds by proposing a method that achieves competitive performance on both dense and sparse point clouds while being trained only with dense data.
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds with minimal unlabelled sparse point clouds, thereby saving additional sparse data collection, annotation and retraining costs. In this work, we propose a novel method for point cloud based object recognition with competitive performance with state-of-art methods on dense and sparse point clouds while being trained only with dense point clouds.