3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
Published in BMVC, 2018
Recommended citation: Mandikal, P.*, Navaneet K L*, Agarwal, M.* and Babu, R.V. (2018). "3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image." British Machine Vision Conference (BMVC). /files/02-lmnet.pdf
In 3D-LMNet, we match the latent embeddings of 2D and 3D encoder networks to facilitate effective 3D reconstruction from 2D image. We also explore generating multiple plausible reconstructions from ambigous images.