Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap. (arXiv:2203.03833v2 [cs.CV] UPDATED)

Semantic analyses of object point clouds are largely driven by releasing of
benchmarking datasets, including synthetic ones whose instances are sampled
from object CAD models. However, learning from synthetic data may not
generalize to practical scenarios, where point clouds are typically incomplete,
non-uniformly distributed, and noisy. Such a challenge of Simulation-to-Reality
(Sim2Real) domain gap could be mitigated via learning algorithms of domain
adaptation; however, we argue that generation of synthetic point clouds via
more physically realistic rendering is a powerful …

arxiv cv gap noise self-training training