Runyi Yang

Runyi Yang

Auto-generated profile, based on publicly available information

Runyi Yang

INSAIT, Sofia University, Sofia, Sofia, Bulgaria

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 November 2023 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YSyongliang Shi
yongliang Shi
RYRunyi Yang
Runyi Yang
ZWZirui Wu
Zirui Wu
PLPengfei Li
Pengfei Li
CLCaiyun Liu
Caiyun Liu
GZGuyue Zhou
Guyue Zhou

9 November 2026
Verified
Conference Paper
Open access
QWQizhe Wei
Qizhe Wei
XGXianda Guo
Xianda Guo
SXShaocong Xu
Shaocong Xu
HLHong Li
Hong Li
RYRunyi Yang
Runyi Yang
HZHao Zhao
Hao Zhao

4 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
YHYuxin Huang
Yuxin Huang
AYAndong Yang
Andong Yang
ZWZirui Wu
Zirui Wu
YCYuantao Chen
Yuantao Chen
RYRunyi Yang
Runyi Yang
GZGuyue Zhou
Guyue Zhou
It has been shown that learning radiance fields with depth rendering and depth supervision can effectively promote the quality and convergence of view synthesis. However, this paradigm requires input RGB-D sequences to be synchronized, hindering its usage in the UAV city modeling scenario. As there exists asynchrony between RGB images and depth images due to high-speed flight, we propose a novel time-pose function, which is an implicit network that maps timestamps to $\rm SE(3)$ elements. To simplify the training process, we also design a joint optimization scheme to jointly learn the large-scale depth-regularized radiance fields and the time-pose function. Our algorithm consists of three steps: (1) time-pose function fitting, (2) radiance field bootstrapping, (3) joint pose error compensation and radiance field refinement. In addition, we propose a large synthetic dataset with diverse controlled mismatches and ground truth to evaluate this new problem setting systematically. Through extensive experiments, we demonstrate that our method outperforms baselines without regularization. We also show qualitatively improved results on a real-world asynchronous RGB-D sequence captured by drone. Codes, data, and models will be made publicly available.

1 May 2024 in arXiv
Verified
Preprint
Open access
PDF file
RYRunyi Yang
Runyi Yang
ZZZhenxin Zhu
Zhenxin Zhu
ZJZhou Jiang
Zhou Jiang
BYBaijun Ye
Baijun Ye
XCXiaoxue Chen
Xiaoxue Chen
HZHao Zhao
Hao Zhao
Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory. We credit this high memory footprint to the lack of consideration for the relationship between primitives. In this paper, we propose a memory-efficient Gaussian field named SUNDAE with spectral pruning and neural compensation. On one hand, we construct a graph on the set of Gaussian primitives to model their relationship and design a spectral down-sampling module to prune out primitives while preserving desired signals. On the other hand, to compensate for the quality loss of pruning Gaussians, we exploit a lightweight neural network head to mix splatted features, which effectively compensates for quality losses while capturing the relationship between primitives in its weights. We demonstrate the performance of SUNDAE with extensive results. For example, SUNDAE can achieve 26.80 PSNR at 145 FPS using 104 MB memory while the vanilla Gaussian splatting algorithm achieves 25.60 PSNR at 160 FPS using 523 MB memory, on the Mip-NeRF360 dataset. Codes are publicly available at https://runyiyang.github.io/projects/SUNDAE/.