AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

BallGAN: 3D-aware Image Synthesis with a Spherical Background

Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun, Youngjung Uh

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: 3D-aware generative radiance fields · 8 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
add spherical opaque background to StyleNeRF (BallGAN-S) on CompCarsStyleNeRF · CompCars 256^2FID: 8 -> 4.26Improved
add foreground density loss L_fg (ablation)BallGAN · FFHQ (batch 16)FID: 7.87 -> 6.82Improved
add background transmittance loss L_bg alone (ablation)BallGAN · FFHQ (batch 16)FID: 7.87 -> 7.88No clear effect
add L_bg on top of L_fg (ablation)BallGAN · FFHQ (batch 16)FID: 6.82 -> 6.13Improved
use cube instead of sphere background (ablation)BallGAN-S · CompCarsconvergenceHurt
use sphere background instead of NeRF++ background (ablation)NeRF foreground, single scene overfitting lf-basket · lf-basket SSOforeground separation and depth (qualitative)Improved
replace EG3D with BallGAN sphere backgroundEG3D · FFHQ 512^2pose error: 0.007 -> 0.005Improved
replace EG3D with BallGAN sphere backgroundEG3D · FFHQ 512^2FID: 4.7 -> 5.67Hurt
replace EG3D with BallGAN sphere backgroundEG3D · AFHQv2-Cats 512^2FID: 2.77 -> 4.72Hurt
replace EG3D with BallGAN sphere backgroundEG3D · FFHQ COLMAPreconstructed points (10^4): 78 -> 79No clear effect
add sphere background replacing NeRF++ in EpiGRAF (ablation)EpiGRAF · FFHQ and Catsforeground separation (qualitative)Improved

Later papers that compared with this method

1 later accepted paper reports BallGAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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