AI Paper Atlas

Research map / 3D vision / Face and shape

HoloGAN: Unsupervised Learning of 3D Representations From Natural Images

Thu Nguyen-Phuoc, Chuan Li, Lucas Theis, Christian Richardt, Yong-Liang Yang

ICCV 2019 · 3D vision › Face and shape · approach: 3D shape generative modeling · 350 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
apply random 3D rigid-body transformations during training (ablation)HoloGAN · object datasetspose control / disentanglementImproved
use learnt constant tensor with z as AdaIN style instead of feeding z to first layer (ablation)HoloGAN · object datasetspose-identity disentanglementImproved
add identity regulariser for 128x128 generation (ablation)HoloGAN · 128x128 imagesimage quality / pose variationImproved
use HoloGAN instead of WGAN-GPWGAN-GP · Chairs 64x64KID (mean x100): 9.43 ± 0.24 -> 1.54 ± 0.07Improved
use HoloGAN instead of WGAN-GPWGAN-GP · Cars 64x64KID (mean x100): 15.57 ± 0.29 -> 2.16 ± 0.09Improved
use HoloGAN instead of WGAN-GPWGAN-GP · CelebA 64x64KID (mean x100): 1.63 ± 0.09 -> 2.87 ± 0.09Hurt
use HoloGAN instead of DCGANDCGAN · CelebA 64x64KID (mean x100): 1.81 ± 0.09 -> 2.87 ± 0.09Hurt
use HoloGAN instead of DCGANDCGAN · Cars 64x64KID (mean x100): 4.78 ± 0.11 -> 2.16 ± 0.09Improved

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