AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

Ruizhi Shao, Hongwen Zhang, He Zhang, Mingjia Chen, Yan-Pei Cao, Tao Yu, Yebin Liu

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 78 citations (OpenAlex)

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 the shared Double MLP to associate the surface and radiance fields (ablation)DoubleField · TwindomPSNR: 22.01 -> 22.95Improved
Add the shared Double MLP to associate the surface and radiance fields (ablation)DoubleField · THuman2.0PSNR: 23.42 -> 24.23Improved
Use the view-to-view transformer instead of average pooling for multi-view fusion (ablation)DoubleField · TwindomPSNR: 22.53 -> 22.95Improved
Use the view-to-view transformer instead of average pooling for multi-view fusion (ablation)DoubleField · THuman2.0PSNR: 23.89 -> 24.23Improved
Add colored encoding of high-resolution RGB inputs (ablation)DoubleField · TwindomPSNR: 22.89 -> 22.95No clear effect
Add colored encoding of high-resolution RGB inputs (ablation)DoubleField · THuman2.0PSNR: 24.11 -> 24.23Improved
Use high-resolution pixels during person-specific finetuning (ablation)DoubleField · TwindomPSNR: 23.28 -> 23.56Improved
Use high-resolution pixels during person-specific finetuning (ablation)DoubleField · THuman2.0PSNR: 24.97 -> 25.10Improved
Finetune the proposed method for 4,000 iterationsDoubleField · TwindomChamfer: 0.737 -> 0.711Improved
Finetune the proposed method for 4,000 iterationsDoubleField · TwindomPSNR: 22.95 -> 23.56Improved
Finetune the proposed method for 4,000 iterationsDoubleField · THuman2.0Chamfer: 0.696 -> 0.662Improved

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