publications updated

content/authors/Zhiyang-Dou/_index.md

@@ -30,7 +30,7 @@ department:
 
 # Organizations/Affiliations
 organizations:
-- name: University of Hong Kong
+- name: The University of Hong Kong
   # url: ""
 
 # Short bio (displayed in user profile at end of posts)
@@ -42,14 +42,16 @@ interests:
 
 education:
   courses:
+  - course: Visiting PhD in Computer Science
+    institution: University of Pennsylvania
+    year: 2025 (expected)
   - course: PhD in Computer Science
-    institution: University of Hong Kong
+    institution: The University of Hong Kong
     year: 2025 (expected)
   - course: Computer Science
     institution: Shandong University
     year: 2020
 
-
 # Social/Academic Networking
 # For available icons, see: https://sourcethemes.com/academic/docs/page-builder/#icons
 #   For an email link, use "fas" icon pack, "envelope" icon, and a link in the

content/publication/cat++-2024/index.md

@@ -0,0 +1,57 @@
+---
+# Documentation: https://wowchemy.com/docs/managing-content/
+
+title: 'Coverage Axis++: Efficient Skeletal Points Selection for 3D Shape Skeletonization'
+subtitle: 'Equal contributions: Zimeng and Zhiyang'
+summary: 
+authors:
+- Zimeng Wang
+- Zhiyang Dou
+- Rui Xu
+- Cheng Lin
+- Yuan Liu
+- Xiaoxiao Long
+- Shiqing Xin
+- Taku Komura
+- Xiaoming Yuan
+- Wenping Wang
+
+
+tags:
+- 'Geometric Modeling'
+- 'Medial Axis Transform'
+
+categories: []
+date: '2024-06-27'
+lastmod: 2024-06-27T21:34:50Z
+featured: false
+draft: false
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: ''
+  focal_point: ''
+  preview_only: false
+
+# Projects (optional).
+#   Associate this post with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects: []
+publishDate: '2024-06-27T21:34:50.388741Z'
+publication_types:
+# 1 Conference paper
+# 2 Journal article
+# 3 Preprint
+# 4 Report
+# 5 Book
+# 6 Book section
+# 7 Thesis
+# 8 Patent
+- '1'
+abstract:      We introduce Coverage Axis++, a novel and efficient approach to 3D shape skeletonization. The current state-of-the-art approaches for this task often rely on the watertightness of the input or suffer from substantial computational costs, thereby limiting their practicality. To address this challenge, Coverage Axis++ proposes a heuristic algorithm to select skeletal points, offering a high-accuracy approximation of the Medial Axis Transform (MAT) while significantly mitigating computational intensity for various shape representations. We introduce a simple yet effective strategy that considers shape coverage, uniformity, and centrality to derive skeletal points. The selection procedure enforces consistency with the shape structure while favoring the dominant medial balls, which thus introduces a compact underlying shape representation in terms of MAT. As a result, Coverage Axis++ allows for skeletonization for various shape representations (e.g., water-tight meshes, triangle soups, point clouds), specification of the number of skeletal points, few hyperparameters, and highly efficient computation with improved reconstruction accuracy. Extensive experiments across a wide range of 3D shapes validate the efficiency and effectiveness of Coverage Axis++. \ZY{Our codes are available at \url{https://github.com/Frank-ZY-Dou/Coverage_Axis}.
+publication: 'SGP 2024'
+---

content/publication/emdm-2024/index.md

@@ -0,0 +1,57 @@
+---
+# Documentation: https://wowchemy.com/docs/managing-content/
+
+title: 'EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation'
+subtitle: 'Project Lead: Zhiyang Dou'
+summary: 
+authors:
+- Wenyang Zhou
+- Zhiyang Dou
+- Zeyu Cao
+- Zhouyingcheng Liao
+- Jingbo Wang
+- Wenjia Wang
+- Yuan Liu
+- Taku Komura
+- Wenping Wang
+- Lingjie Liu
+
+
+tags:
+- '3D human motion generation'
+- 'Diffusion Model'
+
+categories: []
+date: '2024-07-22'
+lastmod: 2024-07-22T21:34:50Z
+featured: false
+draft: false
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: ''
+  focal_point: ''
+  preview_only: false
+
+# Projects (optional).
+#   Associate this post with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects: []
+publishDate: '2024-07-22T21:34:50.388741Z'
+publication_types:
+# 1 Conference paper
+# 2 Journal article
+# 3 Preprint
+# 4 Report
+# 5 Book
+# 6 Book section
+# 7 Thesis
+# 8 Patent
+- '1'
+abstract: We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. On the one hand, previous works, like motion latent diffusion, conduct diffusion within a latent space for efficiency, but learning such a latent space can be a non-trivial effort. On the other hand, accelerating generation by naively increasing the sampling step size, e.g., DDIM, often leads to quality degradation as it fails to approximate the complex denoising distribution. To address these issues, we propose EMDM, which captures the complex distribution during multiple sampling steps in the diffusion model, allowing for much fewer sampling steps and significant acceleration in generation. This is achieved by a conditional denoising diffusion GAN to capture multimodal data distributions among arbitrary (and potentially larger) step sizes conditioned on control signals, enabling fewer-step motion sampling with high fidelity and diversity. To minimize undesired motion artifacts, geometric losses are imposed during network learning. As a result, EMDM achieves real-time motion generation and significantly improves the efficiency of motion diffusion models compared to existing methods while achieving high-quality motion generation. Our code is available at \url{https://github.com/Frank-ZY-Dou/EMDM}.
+publication: 'ECCV 2024'
+---

content/publication/surfd-2024/index.md

@@ -0,0 +1,59 @@
+---
+# Documentation: https://wowchemy.com/docs/managing-content/
+
+title: 'Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models'
+subtitle: 'Equal contributions: Zhengming and Zhiyang'
+summary: 
+authors:
+- Zhengming Yu
+- Zhiyang Dou
+- Xiaoxiao Long 
+- Cheng Lin
+- Zekun Li
+- Yuan Liu 
+- Norman Müller
+- Taku Komura
+- Marc Habermann
+- Christian Theobalt
+- Xin Li
+- Wenping Wang
+
+tags:
+- 'Shape Generation'
+- 'Shape Reconstruction'
+- 'Topology'
+
+categories: []
+date: '2024-07-21'
+lastmod: 2024-07-22T21:34:50Z
+featured: false
+draft: false
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: ''
+  focal_point: ''
+  preview_only: false
+
+# Projects (optional).
+#   Associate this post with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects: []
+publishDate: '2024-07-22T21:34:50.388741Z'
+publication_types:
+# 1 Conference paper
+# 2 Journal article
+# 3 Preprint
+# 4 Report
+# 5 Book
+# 6 Book section
+# 7 Thesis
+# 8 Patent
+- '1'
+abstract: We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited topologies and poor geometry details. To generate high-quality surfaces of arbitrary topologies, we use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. Furthermore, we propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF and support high-resolution mesh extraction. We further show that our new pipeline significantly outperforms the prior approaches to learning the distance fields, such as the grid-based AutoEncoder, which is not scalable and incapable of learning accurate UDF. In addition, we adopt a curriculum learning strategy to efficiently embed various surfaces. With the pretrained shape latent space, we employ a latent diffusion model to acquire the distribution of various shapes. Extensive experiments are presented on using Surf-D for unconditional generation, category conditional generation, image conditional generation, and text-to-shape tasks. The experiments demonstrate the superior performance of Surf-D in shape generation across multiple modalities as conditions.
+publication: 'ECCV 2024'
+---

content/publication/tlcontrol-2024/index.md

@@ -0,0 +1,53 @@
+---
+# Documentation: https://wowchemy.com/docs/managing-content/
+
+title: 'TLControl: Trajectory and Language Control for Human Motion Synthesis'
+subtitle: ''
+summary: 
+authors:
+- Weilin Wan
+- Zhiyang Dou
+- Taku Komura
+- Wenping Wang
+- Dinesh Jayaraman
+- Lingjie Liu
+
+
+
+tags:
+- '3D human motion generation'
+
+categories: []
+date: '2024-07-21'
+lastmod: 2024-07-21T21:34:50Z
+featured: false
+draft: false
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: ''
+  focal_point: ''
+  preview_only: false
+
+# Projects (optional).
+#   Associate this post with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects: []
+publishDate: '2024-07-21T21:34:50.388741Z'
+publication_types:
+# 1 Conference paper
+# 2 Journal article
+# 3 Preprint
+# 4 Report
+# 5 Book
+# 6 Book section
+# 7 Thesis
+# 8 Patent
+- '1'
+abstract: Controllable human motion synthesis is essential for applications in AR/VR, gaming, movies, and embodied AI. Existing methods often focus solely on either language or full trajectory control, lacking precision in synthesizing motions aligned with user-specified trajectories, especially for multi-joint control. To address these issues, we present TLControl, a new method for realistic human motion synthesis, incorporating both low-level trajectory and high-level language semantics controls. Specifically, we first train a VQ-VAE to learn a compact latent motion space organized by body parts. We then propose a Masked Trajectories Transformer to make coarse initial predictions of full trajectories of joints based on the learned latent motion space, with user-specified partial trajectories and text descriptions as conditioning. Finally, we introduce an efficient test-time optimization to refine these coarse predictions for accurate trajectory control. Experiments demonstrate that TLControl outperforms the state-of-the-art in trajectory accuracy and time efficiency, making it practical for interactive and high-quality animation generation.
+publication: 'ECCV 2024'
+---

content/talk/202307_iccv/index.md

@@ -1,7 +1,7 @@
 ---
 # Documentation: https://wowchemy.com/docs/managing-content/
 
-title: '4 papers accepted at ICCV 2023'
+title: 'Four papers accepted at ICCV 2023'
 subtitle: ''
 summary: 'Zolly, PhaseMP, TORE, DualMeshUDF were accepted at ICCV 2023. Congratulations!'
 

content/talk/202406_sgp/index.md

@@ -0,0 +1,36 @@
+---
+# Documentation: https://wowchemy.com/docs/managing-content/
+
+title: 'One papers accepted at SGP 2024'
+subtitle: ''
+summary: 'Zolly, PhaseMP, TORE, DualMeshUDF were accepted at ICCV 2023. Congratulations!'
+
+
+categories: []
+date: '2023-07-01'
+lastmod: 2021-01-15T21:34:50Z
+featured: false
+draft: false
+authors:
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: ''
+  focal_point: ''
+  preview_only: false
+
+---
+
+Four papers were accepted at ICCV 2023. Congratulations!
+
+[Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction](https://wenjiawang0312.github.io/projects/zolly/)
+
+[PhaseMP: Robust 3D Pose Estimation via Phase-conditioned Human Motion Prior
+](https://rubbly.cn/publications/phaseMP/)
+
+[TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer
+](https://frank-zy-dou.github.io/projects/Tore/index.html)
+
+[Surface Extraction from Neural Unsigned Distance Fields](https://cong-yi.github.io/projects/dualmeshudf/)