atlas

Research map / 3D vision / NeRF and radiance fields

Pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis

CVPR 2021 · 3D vision › NeRF and radiance fields · approach: 3D-aware generative radiance fields · 698 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 pi-GAN instead of the strongest listed baseline, GRAF3D-aware image synthesis · CelebA 128×128FID: 41.1 -> 14.7Helped
use pi-GAN instead of the strongest listed baseline, GRAF3D-aware image synthesis · Cats 128×128FID: 28.9 -> 16.8Helped
use pi-GAN instead of the strongest listed baseline, GRAF3D-aware image synthesis · CARLA 128×128FID: 41.7 -> 29.2Helped
add sine activations instead of ReLU positional encoding, with concatenation conditioning (ablation)pi-GAN radiance-field representation · CelebA 64×64FID: 32.0 -> 21.6Helped
add mapping-network FiLM conditioning instead of concatenation, with ReLU positional encoding (ablation)pi-GAN radiance-field representation · CelebA 64×64FID: 32.0 -> 26.8Helped
add both sine activations and mapping-network FiLM conditioning (ablation)pi-GAN radiance-field representation · CelebA 64×64FID: 32.0 -> 5.15Helped

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