1 code implementation • 11 Aug 2023 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
MS3D++ provides a straightforward approach to domain adaptation by generating high-quality pseudo-labels, enabling the adaptation of 3D detectors to a diverse range of lidar types, regardless of their density.
1 code implementation • 5 Apr 2023 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
Our proposed Kernel-Density Estimation (KDE) Box Fusion method fuses box proposals from multiple domains to obtain pseudo-labels that surpass the performance of the best source domain detectors.
1 code implementation • 14 Sep 2022 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
With SEE-VCN, we obtain a unified representation of objects across datasets, allowing the network to focus on learning geometry, rather than overfitting on scan patterns.
1 code implementation • 17 Nov 2021 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Stewart Worrall, Eduardo Nebot
Sampling discrepancies between different manufacturers and models of lidar sensors result in inconsistent representations of objects.
1 code implementation • 23 Mar 2021 • Darren Tsai, Stewart Worrall, Mao Shan, Anton Lohr, Eduardo Nebot
We propose a robust calibration pipeline that optimises the selection of calibration samples for the estimation of calibration parameters that fit the entire scene.