AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

3D-Aware Indoor Scene Synthesis with Depth Priors

Zifan Shi, Yujun Shen, Jiapeng Zhu, Dit-Yan Yeung, Qifeng Chen

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: 3D-aware generative radiance fields · 28 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 depth prediction losses (real and fake) (ablation)DepthGAN · LSUN bedroom 128x128FID (Depth): 26.518 -> 18.874Improved
add depth prediction losses (real and fake) (ablation)DepthGAN · LSUN bedroom 128x128Rotation consistency (RC): 0.711 -> 0.530Improved
add depth prediction loss on fake images (ablation)DepthGAN · LSUN bedroom 128x128FID: 5.441 -> 4.040Improved
add RGB rotation consistency loss (ablation)DepthGAN · LSUN bedroom 128x128Rotation consistency (RC): 0.716 -> 0.530Improved
add RGB rotation consistency loss (ablation)DepthGAN · LSUN bedroom 128x128FID: 5.038 -> 4.040Improved
add depth rotation consistency loss (ablation)DepthGAN · LSUN bedroom 128x128Rotation precision (RP): 0.152 -> 0.040Improved
add depth rotation consistency loss (ablation)DepthGAN · LSUN bedroom 128x128FID (Depth): 8.315 -> 18.874Hurt
add depth-feature conditioning of the appearance renderer (ablation)DepthGAN · LSUN bedroom 128x128FID: 24.062 -> 4.040Improved
add depth-feature conditioning of the appearance renderer (ablation)DepthGAN · LSUN bedroom 128x128FID (Depth): 119.917 -> 18.874Improved
add conditioning and rotation losses (ablation)DepthGAN · LSUN bedroom 128x128FID: 2.793 -> 4.040Hurt
use depth prior with dual-path generator instead of GIRAFFEDepthGAN · LSUN bedroom 256x256FID: 44.232 -> 4.797Improved
give baselines depth supervision (GRAF to GRAF-RGBD)GRAF · LSUN bedroom 256x256FID: 66.856 -> 194.260Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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