AI Paper Atlas

Research map / 3D vision / Face and shape

Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation

Giorgos Bouritsas, Sergiy Bokhnyak, Stylianos Ploumpis, Michael Bronstein, Stefanos Zafeiriou

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 185 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use fixed consistent spiral ordering instead of random per mesh and epoch (linear projection) (ablation)Spiral convolution · COMA (ordering consistency, simple Neural3DMM, latent size 16)reconstruction error (mm): 0.829 -> 0.635Improved
use fixed consistent spiral ordering instead of random per mesh and epoch (LSTM) (ablation)Spiral LSTM operator · COMA (ordering consistency, simple Neural3DMM, latent size 16)reconstruction error (mm): 0.888 -> 0.792Improved
use fixed ordering instead of random orientation per epoch (linear projection) (ablation)Spiral convolution · COMA (ordering consistency, simple Neural3DMM, latent size 16)reconstruction error (mm): 0.951 -> 0.635Improved
replace LSTM over the spiral with linear projection (fixed ordering) (ablation)Spiral operator · COMA (ordering consistency, simple Neural3DMM, latent size 16)reconstruction error (mm): 0.792 -> 0.635Improved
replace MoNet 9 kernels with spiral convolution (ablation)MoNet 9 kernels · COMA (latent size 16, simple Neural3DMM architecture)reconstruction error (mm): 0,708 -> 0,635Improved
replace GAT 9 kernels with spiral convolution (ablation)GAT 9 kernels · COMA (latent size 16, simple Neural3DMM architecture)reconstruction error (mm): 0,762 -> 0,635Improved
replace FeastNet 9 kernels with spiral convolution (ablation)FeastNet 9 kernels · COMA (latent size 16, simple Neural3DMM architecture)reconstruction error (mm): 0,750 -> 0,635Improved
replace over-parametrised MoNet 25 kernels with spiral convolution (ablation)MoNet 25 kernels · COMA (latent size 16, simple Neural3DMM architecture)reconstruction error (mm): 0,583 -> 0,635Hurt
replace over-parametrised FeastNet 25 kernels with spiral convolution (ablation)FeastNet 25 kernels · COMA (latent size 16, simple Neural3DMM architecture)reconstruction error (mm): 0,623 -> 0,635Hurt
replace over-parametrised GAT 25 kernels with spiral convolution (ablation)GAT 25 kernels · COMA (latent size 16, simple Neural3DMM architecture)reconstruction error (mm): 0,732 -> 0,635Improved
replace MoNet 9 kernels with spiral convolution (ablation)MoNet 9 kernels · COMA (latent size 16, simple Neural3DMM architecture)inference time per mesh (ms): 10,55 -> 8,18Improved
replace spectral ChebNet filters with spiral convolution (ablation)COMA autoencoder · COMA and DFAUST (varying latent sizes)generalisation errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy