DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering
This work addresses the challenge of creating photo-realistic human models for applications like virtual reality or animation, though it appears incremental as it builds on existing neural field techniques.
The authors tackled the problem of high-fidelity human reconstruction and rendering by introducing DoubleField, a framework that combines surface and radiance fields, resulting in significant improvements in geometry and appearance quality validated on multiple datasets.
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. Please refer to our project page: http://www.liuyebin.com/dbfield/dbfield.html.