We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields.
To handle boundary-level label noise, we also propose a variant ``PNAL-boundary " with a progressive boundary label cleaning strategy.
To this end, we propose a novel transformer-based 3DQA framework "3DQA-TR", which consists of two encoders for exploiting the appearance and geometry information, respectively.
Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value.
However, there remains a much more difficult and under-explored issue on how to generalize the learned skills over unseen object categories that have very different shape geometry distributions.