AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields

Yuedong Chen, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 33 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 region-aware encoder (Swin-T instead of pSp CNN encoder) (ablation)Sem2NeRF · CelebAMask-HQsmall-region mask sensitivity (qualitative)Improved
add region-aware ray sampling in decoder (ablation)Sem2NeRF · CelebAMask-HQregion sensitivity and image quality (qualitative)Improved
add contour and distance-field input augmentation (ablation)Sem2NeRF · CelebAMask-HQedge sharpness (qualitative)Improved
add random-pose GAN loss with discriminator (ablation)Sem2NeRF · CelebAMask-HQartifacts across views (qualitative)Improved
use Sem2NeRF instead of pSpmask-to-NeRF baseline · CelebAMask-HQ @128x128FID: 55.56 -> 41.52Improved
use Sem2NeRF instead of pix2pixHD with inversionmask-to-NeRF baseline · CelebAMask-HQ @128x128runtime (s): 161.59 -> 0.18Improved

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