AI Paper Atlas

Research map / 3D vision / Face and shape

Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler

ICLR 2021 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 20 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
Train the inverse graphics network on StyleGAN-generated multi-view data instead of Pascal3D dataInverse graphics network · Pascal3D test2D IOU: 0.80 -> 0.76Hurt
Train the inverse graphics network on StyleGAN-generated multi-view data instead of Pascal3D dataInverse graphics network · StyleGAN test2D IOU: 0.81 -> 0.95Improved
Train on the StyleGAN-generated dataset rather than Pascal3DInverse graphics network · Pascal3D testoverall user preference: 25.9% -> 57.5%Improved
Train on the StyleGAN-generated dataset rather than Pascal3DInverse graphics network · Pascal3D testshape user preference: 26.4% -> 61.6%Improved
Train on the StyleGAN-generated dataset rather than Pascal3DInverse graphics network · Pascal3D testtexture user preference: 32.8% -> 56.3%Improved
Use multi-view consistency loss during training (ablation)Inverse graphics network · 3D reconstructionshape and texture qualityImproved
Use perceptual loss during training (ablation)Inverse graphics network · 3D reconstructiontexture realismImproved
Fine-tune StyleGAN jointly with the mapping network (ablation)StyleGAN-R · 3D neural renderingconsistency of shape, texture and backgroundImproved
Initialize cameras with coarse view bins instead of keypoints and SfMInverse graphics network · StyleGAN test2D IOU: 0.953 -> 0.952No clear effect
Optimize the original StyleGAN latent code directly for image reconstruction instead of using the mapping network and fine-tuned StyleGAN-RStyleGAN image editing · Viewpoint controlreconstruction qualityHurt
Use the mapping network without fine-tuning StyleGAN (ablation)StyleGAN neural renderer · 3D neural renderingconsistency of shape, texture and backgroundHurt

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