Search Results for author: Hiroyuki Sato

Found 8 papers, 3 papers with code

Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segments

no code implementations26 Mar 2024 Yusuke Takimoto, Hikari Takehara, Hiroyuki Sato, Zihao Zhu, Bo Zheng

In the film and gaming industries, achieving a realistic hair appearance typically involves the use of strands originating from the scalp.

Inverse Rendering

BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation

no code implementations30 Jan 2024 Zhennan Wu, Yang Li, Han Yan, Taizhang Shang, Weixuan Sun, Senbo Wang, Ruikai Cui, Weizhe Liu, Hiroyuki Sato, Hongdong Li, Pan Ji

A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed.

Denoising Scene Generation

Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis

1 code implementation ICML 2018 Hiroyuki Kasai, Hiroyuki Sato, Bamdev Mishra

Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large, but finite number of loss functions on a Riemannian manifold.

Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport

1 code implementation18 Feb 2017 Hiroyuki Sato, Hiroyuki Kasai, Bamdev Mishra

In recent years, stochastic variance reduction algorithms have attracted considerable attention for minimizing the average of a large but finite number of loss functions.

Low-Rank Matrix Completion Riemannian optimization

Riemannian stochastic variance reduced gradient on Grassmann manifold

1 code implementation24 May 2016 Hiroyuki Kasai, Hiroyuki Sato, Bamdev Mishra

In this paper, we propose a novel Riemannian extension of the Euclidean stochastic variance reduced gradient algorithm (R-SVRG) to a compact manifold search space.

Low-Rank Matrix Completion Riemannian optimization +1

Cannot find the paper you are looking for? You can Submit a new open access paper.