In this paper, we study the problem of continuous 3D shape representations. The majority of
existing successful methods are coordinate-based implicit neural representations. However, …

Training machines to synthesize diverse handwritings is an intriguing task. Recently, RNN-based
methods have been proposed to generate stylized online Chinese characters. However…

View synthesis aims to produce unseen views from a set of views captured by two or more
cameras at different positions. This task is non-trivial since it is hard to conduct pixel-level …

Automatic deformation of cranial models has a significant effect on the ergonomic design of
headgears. Previously, manual customization of the template model was required before it …

Head-related product design is significantly enhanced by a thorough understanding of the
morphological differences in human heads between genders. Existing head variation studies …

We propose SIR, an efficient method to decompose differentiable shadows for inverse
rendering on indoor scenes using multi-view data, addressing the challenges in accurately …

Realistic simulation of dynamic scenes requires accurately capturing diverse material
properties and modeling complex object interactions grounded in physical principles. However, …

DTW The lower DTW distance, the better quality of the generated characters. For a more robust
evaluation metric, we normalize the DTW distance by the length of real online characters …

Drying pretreatment of sediment samples can introduce errors in the determination of phosphorus
(P) forms and the assessment of their biological effectiveness. Therefore, it is crucial to …

SiO 2 thin films are deposited by radio frequency (RF) plasma-enhanced chemical vapor
deposition (PECVD) technique using SiH 4 and N 2 O as precursor gases. The stoichiometry of …