Jiaojiao Ye

Jiaojiao Ye

Auto-generated profile, based on publicly available information

Jiaojiao Ye

Department of Computer Science, University of Oxford, Oxford, UK

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
11 August 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
ACAiling Cheng
Ailing Cheng
JYJiaojiao Ye
Jiaojiao Ye
FYFei Yang
Fei Yang
SLShufang Lu
Shufang Lu
FGFei Gao
Fei Gao
Aiming at the accurate and effective coaxiality measurement of twist drills with irregular surface, an optical measurement mechanism is proposed in this article. First, a high-precision rotation instrument based on four core units is designed, which can obtain 3-D point cloud data of twist drills at all angles. Second, in the data processing stage, an improved robust Gaussian mixture model is proposed for accurate and rapid blade back segmentation. To improve the measurement efficiency, a rapid reconstruction method of twist drill axis based on orthogonal synthesis is proposed, which can rapidly locate the maximum deviation between the actual axis and the reference by using the extracted blade back data. Finally, by calculating the maximum radial Euclidean distance from the benchmark, the coaxiality error of the twist drill is obtained. Compared with other measurement methods, the experimental results show that our proposed method performs well with high efficiency of less than 3 s/pc and the average measurement error is about 0.020 mm. The experimental results and uncertainty analysis show that the proposed method is effective and automatic and can be applied to the coaxiality measurement of twist drills of various specifications.


2 September 2026 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
JZJia-Xing Zhong
Jia-Xing Zhong
KLKai Lu
Kai Lu
JYJiaojiao Ye
Jiaojiao Ye
NTNiki Trigoni
Niki Trigoni
AMAndrew Markham
Andrew Markham
Monocular Video-to-4D generation faces the fundamental challenge of inferring plausible 3D geometry and motion from limited single-view inputs. We present MotionStruct4D, a novel approach that discovers and exploits the underlying motion structure of 3D Gaussian Splatting for high-quality video-to-4D generation. Our key insight is that real-world motion can be effectively decomposed into coarse rigid transformations that capture principal movements, complemented by detailed non-rigid deformations that account for fine-grained details. MotionStruct4D introduces: (1) a self-supervised motion structure discovery module that identifies quasi-rigid parts by preserving spatiotemporal relationships without explicit 3D supervision, and (2) a weighted dense-to-sparse optimization architecture that transitions from dense per-Gaussian deformation to sparse control points, effectively integrating rigid and non-rigid motion components through adaptive weighted fusion. This design addresses the parametric imbalance between rigid and non-rigid motions and effectively models 3D movements across different kinematic patterns. To evaluate our approach on challenging scenarios, we curate a comprehensive benchmark dataset featuring substantial object displacement and diverse articulated motion patterns. Experimental results demonstrate MotionStruct4D’s superior performance in motion fidelity and novel viewpoint synthesis quality, while also providing interpretable motion structure decomposition that reveals meaningful quasi-rigid part segmentation.