Aven-Le Zhou

Aven-Le Zhou

Auto-generated profile, based on publicly available information

Aven-Le Zhou

Department of Industrial Design, Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 October 2020
Verified
Conference Paper
Closed access
NLNate Lannan
Nate Lannan
LZLe Zhou
Le Zhou
GFGuoliang Fan
Guoliang Fan
JHJerome Hausselle
Jerome Hausselle
Human motion analysis is integral to many applications ranging from biomedicine to surveillance and 3D animation. The availability of consumer RGB-D sensors makes motion capture (Mocap) more prevalent and accessible in our daily lives. However, depth-based Mocap (D-Mocap) suffers significant errors and noise due to the limitation of depth sensing, selfocclusion, and many other problems. We present a novel filter-assisted deep learning approach to improve low-quality human motion data (e.g., D-Mocap) by taking advantage of the recent progress in both deep learning and nonlinear Kalman filtering. At the heart of this method is a learned motion manifold through the use of a convolutional autoencoder trained on high-quality, richvariety CMU Mocap data which is used to recover valid human motion from corrupted input. Furthermore, the Tobit Kalman filter (TKF), proposed to handle censored measurements, is used to assist the autoencoder with more kinematic and dynamic constraints. Two structural paradigms are investigated to handle different kinds of data errors by maximizing the synergy between the two integral parts in this work. The experimental results on both simulated and real-world human motion data demonstrate the effectiveness and robustness of the proposed methods to improve the quality of noisy and erroneous Mocap data.

1 August 2024 in Leonardo
Verified
Journal Article
Closed access
PDF file
AZAven Le Zhou
Aven Le Zhou
KZKang Zhang
Kang Zhang
The authors investigate Chinese shanshui (literally, “mountain and water”), ink paintings of the natural landscape, through an interactive art installation entitled Shanshui Journey. By examining shanshui’s philosophy, multiple moving perspectives, and creation and appreciation practices, the work emphasizes motion in nature, memories, and interactive appreciation. These concepts are realized in a digitized room, where each participant’s motion is captured as a line “sketch” and transformed into an ink painting via a custom neural network. Generated paintings are displayed in real time alongside previous works, collectively termed Shanshui Memories, mimicking handscroll interaction. The authors’ approach to shanshui aims to reproduce the Chinese literati art experience, and to raise awareness of this cultural heritage.

28 November 2023
Verified
Conference Paper
Open access
AZAven Le Zhou
Aven Le Zhou
KZKang Zhang
Kang Zhang
DYDavid Yip
David Yip
Perceiving paintings entails more than merely engaging the audience's eyes and brains; their perceptions and experiences of a painting can be intricately connected with body movement. This paper proposes an interactive art approach entitled “Painterly Reality” that facilitates the perception and interaction with paintings in a three-dimensional manner. Its objective is to promote bodily engagement with the painting (i.e., embedded body embodiment and its movement and interaction) to enhance the audience's experience, while maintaining its essence. Unlike two-dimensional interactions, this approach constructs the Painterly Reality by capturing the audience's body embodiment in real-time and embedding into a three-dimensional painterly world derived from a given painting input. Through their body embodiment, the audience can navigate the painterly world and play with magical realism (i.e., interactive painterly objects), fostering meaningful experiences via interactions. The Painterly Reality is subsequently projected through an Augmented Reality Mirror as a live painting and displayed in front of the audience. Hence, the audience can gain enhanced experiences through bodily engagement while simultaneously viewing and appreciating the live painting. The paper implements the proposed approach as an interactive artwork, entitled “Everyday Conjunctive”, with Fong Tse Ka's painting, installed in a local museum which successfully enhances audience experience through bodily engagement.

22 June 2025
Verified
Conference Paper
Open access
YZYoyo Yi-Yao Zhang
Yoyo Yi-Yao Zhang
AZAven-Le Zhou
Aven-Le Zhou

18 December 2025
Verified
Conference Paper
Open access
YMYiran Ma
Yiran Ma
XZXianyue Zhu
Xianyue Zhu
CCChelsea-Xi Chen
Chelsea-Xi Chen
AZAven-Le Zhou
Aven-Le Zhou

25 July 2024
Verified
Conference Paper
Open access
AZAven-Le Zhou
Aven-Le Zhou
YWYu-Ao Wang
Yu-Ao Wang
WWWei Wu
Wei Wu
KZKang Zhang
Kang Zhang
Due to the significant generative capabilities of GenAI (generative artificial intelligence), the art community has actively embraced it to create painterly content. Large text-to-image models can quickly generate aesthetically pleasing outcomes. However, the process can be non-deterministic and often involves tedious trial-and-error as users struggle to formulate effective prompts to achieve their desired results. This paper describes a generative approach that empowers users to easily work with a large text-to-image (TTI) model to create their preferred painterly content. The authors propose a large model personalization method, namely Semantic Injection, to personalize a large TTI model in a given specific artistic style, i.e., Kandinsky’s paintings in Bauhaus era, as the Artist Model. Through working with a Kandinsky expert, the authors first establish a semantic descriptive guideline and a TTI dataset of Kandinsky style and then apply the Semantic Injection method to obtain an Artist Model of Kandinsky, empowering users to create preferred Kandinsky content in a deterministically controllable manner.