Litcius/Paper detail

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

20222022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)75 citationsDOI

Abstract

We introduce DoubleField, a novel framework combining the merits of both surface field and radiance field for high-fidelity human reconstruction and rendering. Within DoubleField, the surface field and radiance field are associated together by a shared feature embedding and a surface-guided sampling strategy. Moreover, a view-to-view transformer is introduced to fuse multi-view features and learn view-dependent features directly from high-resolution inputs. With the modeling power of DoubleField and the view-to-view transformer, our method significantly improves the reconstruction quality of both geometry and appearance, while supporting direct inference, scene-specific high-resolution finetuning, and fast rendering. The efficacy of DoubleField is validated by the quantitative evaluations on several datasets and the qualitative results in a real-world sparse multi-view system, showing its superior capability for high-quality human model reconstruction and photo-realistic free-viewpoint human rendering. Data and source code will be made public for the research purpose.

Topics & Concepts

Computer scienceRendering (computer graphics)RadianceArtificial intelligenceComputer visionHigh fidelityFidelitySurface reconstructionComputer graphics (images)Remote sensingSurface (topology)EngineeringGeographyTelecommunicationsMathematicsElectrical engineeringGeometry3D Shape Modeling and AnalysisAdvanced Vision and ImagingComputer Graphics and Visualization Techniques