Towards Learning Neural Representations from Shadows

Tiwary, Kushagra; Klinghoffer, Tzofi; Raskar, Ramesh

doi:10.1007/978-3-031-19827-4_18

Cited by 7 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it is crucial to design a more powerful rendering representation, and decoupling method to solve these problems; see Refs. [65,66]. In addition, it is worth exploring how applying our ideas to dynamic geometry reconstruction and single-image based geometry reconstruction can improve speed and precision; see Refs.…”

Section: Discussionmentioning

confidence: 99%

Multi-scale hash encoding based neural geometry representation

Deng,

Xiao,

Lang

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

Recently, neural implicit function-based representation has attracted more and more attention, and has been widely used to represent surfaces using differentiable neural networks. However, surface reconstruction from point clouds or multi-view images using existing neural geometry representations still suffer from slow computation and poor accuracy. To alleviate these issues, we propose a multi-scale hash encoding-based neural geometry representation which effectively and efficiently represents the surface as a signed distance field. Our novel neural network structure carefully combines low-frequency Fourier position encoding with multi-scale hash encoding. The initialization of the geometry network and geometry features of the rendering module are accordingly redesigned. Our experiments demonstrate that the proposed representation is at least 10 times faster for reconstructing point clouds with millions of points. It also significantly improves speed and accuracy of multi-view reconstruction. Our code and models are available at https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction.

show abstract

Section: Discussionmentioning

confidence: 99%