AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Spherical Image Generation from a Single Image by Considering Scene Symmetry

AAAI 2021 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 17 citations (OpenAlex)

Read the paperCheck 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 the symmetry-conditioned generation setting instead of 360ICSpherical image generation · SUN360 testFID: 27.5 -> 24.4Helped
Use symmetry-conditioned reconstruction instead of 360ICSpherical image generation · SUN360 testL1: 0.170 -> 0.138Helped
Use symmetry-conditioned reconstruction instead of 360ICSpherical image generation · SUN360 testPSNR: 12.6 -> 14.3Helped
Add the global discriminator (ablation)Ours (gen.) · SUN360 testFID: 27.6 -> 24.4Helped
Add the global discriminator (ablation)Ours (gen.) · SUN360 testL1: 0.171 -> 0.172No clear effect
Add the global discriminator (ablation)Ours (gen.) · SUN360 testPSNR: 12.4 -> 12.4No clear effect
Add the global discriminator (ablation)Ours (rec.) · SUN360 testFID: 46.8 -> 28.1Helped
Add the global discriminator (ablation)Ours (rec.) · SUN360 testL1: 0.135 -> 0.138Hurt
Add the global discriminator (ablation)Ours (rec.) · SUN360 testPSNR: 14.6 -> 14.3Hurt

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