DeepAI AI Chat
Log In Sign Up

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

by   Ruizhi Shao, et al.

We introduce DoubleField, a novel representation combining the merits of both surface field and radiance field for high-fidelity human rendering. Within DoubleField, the surface field and radiance field are associated together by a shared feature embedding and a surface-guided sampling strategy. In this way, DoubleField has a continuous but disentangled learning space for geometry and appearance modeling, which supports fast training, inference, and finetuning. To achieve high-fidelity free-viewpoint rendering, DoubleField is further augmented to leverage ultra-high-resolution inputs, where a view-to-view transformer and a transfer learning scheme are introduced for more efficient learning and finetuning from sparse-view inputs at original resolutions. 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 photo-realistic free-viewpoint human rendering. For code and demo video, please refer to our project page:


page 1

page 8

page 9

page 10


HumanNeRF: Generalizable Neural Human Radiance Field from Sparse Inputs

Recent neural human representations can produce high-quality multi-view ...

Deep Surface Light Fields

A surface light field represents the radiance of rays originating from a...

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

In this work we develop a generalizable and efficient Neural Radiance Fi...

4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions

In this paper, we present a novel and effective framework, named 4K-NeRF...

Efficient Raycasting of View-Dependent Piecewise Constant Representations of Volumetric Data

We present an efficient raycasting-based rendering algorithm for view-de...

HDHumans: A Hybrid Approach for High-fidelity Digital Humans

Photo-real digital human avatars are of enormous importance in graphics,...

SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

In this paper, we propose SelfNeRF, an efficient neural radiance field b...