Eric-Tuan Le — accepted AI-conference papers

2024

MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction

Eric-Tuan Le, Antonis Kakolyris, Petros Koutras, Himmy Tam, Efstratios Skordos, George Papandreou +2

CVPR 2024poster

DensePose provides a pixel-accurate association of images with 3D mesh coordinates but does not provide a 3D mesh while Human Mesh Reconstruction (HMR) systems have high 2D reprojection error as measured by DensePose localization metrics. In this work we introduce MeshPose to jointly tackle DensePos…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2023

StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN

Eric-Tuan Le, Edward Bartrum, Iasonas Kokkinos

ICLR 2023poster

We introduce StyleMorph, a 3D-aware generative model that disentangles 3D shape, camera pose, object appearance, and background appearance for high quality image synthesis. We account for shape variability by morphing a canonical 3D object template, effectively learning a 3D morphable model in an en…

Cited by 3 Source ↗PDF ↗Scholar ↗

2020

Going Deeper With Lean Point Networks

Eric-Tuan Le, Iasonas Kokkinos, Niloy J. Mitra

CVPR 2020poster

In this work we introduce Lean Point Networks (LPNs) to train deeper and more accurate point processing networks by relying on three novel point processing blocks that improve memory consumption, inference time, and accuracy: a convolution-type block for point sets that blends neighborhood informati…

Cited by 33 PDF ↗code ↗Scholar ↗