This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches.
In such scenarios, the ability to accurately simulate the vehicle sensors such as cameras, lidar or radar is essential.
In this paper, we introduce a novel RGB-D based relative pose estimation approach that is suitable for small-overlapping or non-overlapping scans and can output multiple relative poses.
In particular, instead of only performing scene completion from each individual scan, our approach alternates between relative pose estimation and scene completion.
We prove that, with enough data, the LSTM model is indeed as capable of learning whisper characteristics from LFBE features alone compared to a simpler MLP model that uses both LFBE and features engineered for separating whisper and normal speech.
We show a principled way to train this model by combining discriminator losses for both a 3D object arrangement representation and a 2D image-based representation.