Zhiyang (Frank) Dou

Portrait photo of Frank I am a third-year Ph.D. candidate in CG and CV Group at the University of Hong Kong, supervised by Prof. Wenping Wang and Prof. Taku Komura. I received my B. Eng. degree with honors at Shandong University. My undergraduate research advisor is Prof. Shiqing Xin.

Research interests: Character Animation, Geometric Modeling and Processing, Computer Graphics.

Shandong University The University of Hong Kong

News

  • Mar. 2023: One paper conditionally accepted to PNAS Nexus.

  • Mar. 2023: One paper conditionally accepted to SIGGRAPH 2023.

  • Feb. 2023: The code of Coverage Axis in python is released; try it here.

  • Aug. 2022: One paper accepted to SIGGRAPH Asia 2022.

  • Apr. 2022: Started an Internship at Tencent AI Lab.

  • Feb. 2022: One paper accepted to EUROGRAPHICS 2022.

Selected Publications

* Equal contribution.

Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Field
Rui Xu, Zhiyang Dou, Ningna Wang, Shiqing Xin, Shuangmin Chen, Mingyan Jiang, Xiaohu Guo, Wenping Wang, Changhe Tu.
Conditionally Accepted to ACM Transactions on Graphics. SIGGRAPH 2023.

  • project page
  • paper (coming soon)
  • code
  • abstract 
    Estimating normals with globally consistent orientations for a raw point cloud has many downstream geometry processing applications. Despite tremendous efforts in the past decades, it remains challenging to deal with an unoriented point cloud with various imperfections, particularly in the presence of data sparsity coupled with nearby gaps or thin-walled structures. In this paper, we propose a smooth objective function to characterize the requirements of an acceptable winding-number field, which allows one to find the globally consistent normal orientations starting from a set of completely random normals. By taking the vertices of the Voronoi diagram of the point cloud as examination points, we consider the following three requirements: (1) the winding number is either 0 or 1, (2) the occurrences of 1 and the occurrences of 0 are balanced around the point cloud, and (3) the normals align with the outside Voronoi poles as much as possible. Extensive experimental results show that our method outperforms the existing approaches, especially in handling sparse and noisy point clouds, as well as shapes with complex geometry/topology.

RFEPS: Reconstructing Feature-line Equipped Polygonal Surface
Rui Xu, Zixiong Wang, Zhiyang Dou, Chen Zong, Shiqing Xin, Mingyan Jiang, Tao Ju, Changhe Tu.
ACM Transactions on Graphics. SIGGRAPH Asia 2022.

  • project page
  • paper
  • code
  • abstract 
    Feature lines are important geometric cues in characterizing the structure of a CAD model. Despite great progress in both explicit reconstruction and implicit reconstruction, it remains a challenging task to reconstruct a polygonal surface equipped with feature lines, especially when the input point cloud is noisy and lacks faithful normal vectors. In this paper, we develop a multistage algorithm, named RFEPS, to address this challenge. The key steps include (1)denoising the point cloud based on the assumption of local planarity, (2)identifying the feature-line zone by optimization of discrete optimal transport, (3)augmenting the point set so that sufficiently many additional points are generated on potential geometry edges, and (4) generating a polygonal surface that interpolates the augmented point set based on restricted power diagram. We demonstrate through extensive experiments that RFEPS, benefiting from the edge-point augmentation and the feature-preserving explicit reconstruction, outperforms state-of-the-art methods in terms of the reconstruction quality, especially in terms of the ability to reconstruct missing feature lines.

TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer
Zhiyang Dou*, Qingxuan Wu*, Cheng Lin, Zeyu Cao, Qiangqiang Wu, Weilin Wan, Taku Komura, Wenping Wang.
Arxiv 2023.

  • project page
  • paper
  • code
  • abstract 
    In this paper, we introduce a set of simple yet effective TOken REduction (TORE) strategies for Transformer-based Human Mesh Recovery from monocular images. Current SOTA performance is achieved by Transformer-based structures. However, they suffer from high model complexity and computation cost caused by redundant tokens. We propose token reduction strategies based on two important aspects, i.e., the 3D geometry structure and 2D image feature, where we hierarchically recover the mesh geometry with priors from body structure and conduct token clustering to pass fewer but more discriminative image feature tokens to the Transformer. Our method massively reduces the number of tokens involved in high-complexity interactions in the Transformer. This leads to a significantly reduced computational cost while still achieving competitive or even higher accuracy in shape recovery. Extensive experiments across a wide range of benchmarks validate the superior effectiveness of the proposed method. We further demonstrate the generalizability of our method on hand mesh recovery. Our code will be publicly available once the paper is published.

Coverage Axis: Inner Point Selection for 3D Shape Skeletonization
Zhiyang Dou, Cheng Lin, Rui Xu, Lei Yang, Shiqing Xin, Taku Komura, Wenping Wang.
Computer Graphics Forum. Eurographics 2022.

  • project page
  • paper
  • code
  • suppl.
  • abstract 
    In this paper, we present a simple yet effective formulation called Coverage Axis for 3D shape skeletonization. Inspired by the set cover problem, our key idea is to cover all the surface points using as few inside medial balls as possible. This formulation inherently induces a compact and expressive approximation of the Medial Axis Transform (MAT) of a given shape. Different from previous methods that rely on local approximation error, our method allows a global consideration of the overall shape structure, leading to an efficient high-level abstraction and superior robustness to noise. Another appealing aspect of our method is its capability to handle more generalized input such as point clouds and poor-quality meshes. Extensive comparisons and evaluations demonstrate the remarkable effectiveness of our method for generating compact and expressive skeletal representation to approximate the MAT.

Close Contact Behaviors of University and School Students in 10 Typical Indoor Environments.
Nan Zhang, Li Liu, Zhiyang Dou, Xiyue Liu, Xueze Yang, Doudou Miao, Yong Guo, Silan Gu, Yuguo Li, Hua Qian, Jianjian Wei.
Accepted to Environmental Science & Technology 2022, IF=11.4.
System development for close contact behavior collection.
  • paper (coming soon)
  • abstract 
    Close contact, including both short-range airborne and large droplet, is recognized as the main route of SARS-CoV-2 transmission in indoor environments, however exposure risk via this route is difficult to quantify due to a lack of data showing close contact behaviors of people in typical indoor environments. A digital wearable device was developed to capture human close contact behaviors automatically based on semi-supervised learning. We collected a total of 337,056 seconds of indoor close contacts from 194 and a half hours of depth video recordings in 10 typical indoor environments. The relationship between SARS-CoV-2 exposure and close contact behaviors were evaluated based on dispersion characteristics of virus-laden droplets. People in restaurant had the highest close contact ratio (63.8%) and probability of face-to-face pattern (77.6%) during close contacts, while people in shopping center had the highest speak fraction (46.6%). University students had higher exposure potential in dormitories than school students in homes, but less exposure potential in classrooms and graduate student offices than school students in classrooms. Aerosol exposure in volume for both short-range inhalation and direct deposition on facial mucosa were highest in restaurants. Classroom is the main indoor environment for SARS-CoV-2 transmission for school students. The obtained results based on real human close contact behaviors can be used for infection risk assessment and to deploy effective interventions against close contact transmission of COVID-19 and other respiratory infections.

Close Contact Behavior-based COVID-19 Transmission and Interventions in a Subway System
Xiyue Liu*, Zhiyang Dou*, Lei Wang, Boni Su, Tianyi Jin, Yong Guo, Jianjian Wei, Nan Zhang.
Journal of Hazardous Materials 2022, IF=14.2.
Vision system development for human behavior collection and analysis.
  • paper
  • abstract 
    During COVID-19 pandemic, analysis on virus exposure and intervention efficiency in public transports based on real passenger’s close contact behaviors is critical to curb infectious disease transmission. A monitoring device was developed to gather a total of 145,821 close contact data in subways based on semi-supervision learning. A virus transmission model considering both short- and long-range inhalation and deposition was established to calculate the virus exposure. During rush-hour, short-range inhalation exposure is 3.2 times higher than deposition exposure and 7.5 times higher than long-range inhalation exposure of all passengers in the subway. The close contact rate was 56.1 % and the average interpersonal distance was 0.8 m. Face-to-back was the main pattern during close contact. Comparing with random distribution, if all passengers stand facing in the same direction, personal virus exposure through inhalation (deposition) can be reduced by 74.1 % (98.5 %). If the talk rate was decreased from 20 % to 5 %, the inhalation (deposition) exposure can be reduced by 69.3 % (73.8 %). In addition, we found that virus exposure could be reduced by 82.0 % if all passengers wear surgical masks. This study provides scientific support for COVID-19 prevention and control in subways based on real human close contact behaviors.

Top-Down Shape Abstraction Based on Greedy Pole Selection
Zhiyang Dou, Shiqing Xin, Rui Xu, Jian Xu, Yuanfeng Zhou, Shuangmin Chen, Wenping Wang, Xiuyang Zhao, Changhe Tu.
IEEE Transactions on Visualization and Computer Graphics. TVCG 2020.

  • paper
  • abstract 
    Motivated by the fact that the medial axis transform is able to encode nearly the complete shape, we propose to use as few medial balls as possible to approximate the original enclosed volume by the boundary surface. We progressively select new medial balls, in a top-down style, to enlarge the region spanned by the existing medial balls. The key spirit of the selection strategy is to encourage large medial balls while imposing given geometric constraints. We further propose a speedup technique based on a provable observation that the intersection of medial balls implies the adjacency of power cells (in the sense of the power crust). We further elaborate the selection rules in combination with two closely related applications. One application is to develop an easy-to-use ball-stick modeling system that helps non-professional users to quickly build a shape with only balls and wires, but any penetration between two medial balls must be suppressed. The other application is to generate porous structures with convex, compact (with a high isoperimetric quotient) and shape-aware pores where two adjacent spherical pores may have penetration as long as the mechanical rigidity can be well preserved.

Research Experience

IRC The University of Hong Kong Tencent AI Lab

Services

  • Reviewer: CVPR 2023; FSDM 2023; FSDM 2022; MLIS 2022.

  • Teaching Assistant:

    • 2022 COMP3362 Hands-on AI: Experimentation and Applications.

    • 2021 COMP3362 Hands-on AI: Experimentation and Applications.

    • 2020 COMP2120 Computer organization.