AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

3D-Aware Multi-Class Image-to-Image Translation With NeRFs

Senmao Li, Joost van de Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: NeRF for scene decomposition and understanding · 7 citations (OpenAlex)

Read the paper

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
Use 3D-aware multi-class translation instead of StarGANv2CelebA-HQ · CelebA-HQTC: 10.250 -> 3.743Improved
Use 3D-aware multi-class translation instead of StarGANv2AFHQ · AFHQTC: 3.025 -> 2.067Improved
Add the U-net-like adaptor to the initialized model (ablation)3D-aware I2I translation · AFHQTC: 2.612 -> 2.324Improved
Add the hierarchical representation constraint (ablation)3D-aware I2I translation · AFHQFID: 23.1 -> 16.1Improved
Add the relative regularization loss (ablation)3D-aware I2I translation · AFHQTC: 2.204 -> 2.067Improved
Add the relative regularization loss (ablation)3D-aware I2I translation · AFHQFID: 16.1 -> 15.3Improved
Initialize multi-class StyleNeRF from an unconditional StyleNeRF instead of training the conditional model from scratch (ablation)Multi-class StyleNeRF · AFHQ and CelebA-HQimage qualityImproved
Use one mapping network with concatenated class embedding and noise (ablation)Conditional 3D-aware generator · 3D-aware multi-class generationtarget-specific image realismHurt
Use two mapping networks without concatenating their outputs (ablation)Conditional 3D-aware generator · 3D-aware multi-class generation3D-aware generationHurt
Predict 3D location and viewing direction instead of predicting the feature map (ablation)3D-aware I2I adaptor · Image translationimage qualityHurt
Use StarGANv2 for viewpoint-conditioned translationStarGANv2 · CelebA-HQvLPIPS: 0.032 vs 0.101Hurt

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