We study the problem of efficient semantic segmentation of large-scale 3D point clouds.
In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations.
We study the problem of efficient semantic segmentation for large-scale 3D point clouds.
Ranked #3 on Semantic Segmentation on Toronto-3D L002
Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of high variance when applied in complex real world environments.
In this framework, real images are first converted to a synthetic domain representation that reduces complexity arising from lighting and texture.
Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots.