Three-Filters-to-Normal+: Revisiting Discontinuity Discrimination in Depth-to-Normal Translation

no code implementations • 13 Dec 2023 • Jingwei Yang, Bohuan Xue, Yi Feng, Deming Wang, Rui Fan, Qijun Chen

This article introduces three-filters-to-normal+ (3F2N+), an extension of our previous work three-filters-to-normal (3F2N), with a specific focus on incorporating discontinuity discrimination capability into surface normal estimators (SNEs).

6D Pose Estimation using RGB Point Cloud Completion

TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer

no code implementations • 25 Oct 2023 • Xiao Lin, Deming Wang, Guangliang Zhou, Chengju Liu, Qijun Chen

To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information.

6D Pose Estimation using RGB Object