Zhiwen Fan

Recent Projects

CAD(computer-aided design) Drawing Perception

Project Page and Product Page

We release the first a large-scale real-world dataset of over 10,000 CAD drawings with line-grained annotations, covering various types of builds. We also introduce the task of panoptic symbol spotting, which is a relaxation of the traditional symbol spotting problem. By proposing a CNN-GCN method, we build a unified baseline network for the panoptic symbol spotting task. This work can be used integrated in CAD layer analytics in architecture, engineering and construction (AEC) industries to accelerate the efficiency of 3D modeling.

Efficient Multi-view Stereo and Stereo Matching

Recent Multi-view Stereo(MVS) deep models are memory consuming due to the 3D convolution layers when aggregating the cost volume, we proposed a memory and time efficient cost volume formulation which is built upon a standard feature pyramid encoding geometry and context at gradually finer scales， Also, we narrow the depth (or disparity) range of each stage by the depth (or disparity) map from the previous stage to recover the output in a coarser to fine manner. We apply the cascade cost volume to the representative MVS-Net, and obtain a 23.1% improvement on DTU benchmark (1st place), with 50.6% and 74.2% reduction in GPU memory and run-time. It is also the state-of-the-art learning-based method on Tanks and Temples benchmark.

Research

I'm interested in devleoping models for 3D Reconstruction, Graph Convolution for vector graphics and 3D data, Low-level Computer Vision.

Conference Papers:

1. MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
   Rakesh Shrestha, Zhiwen Fan*, Qingkun Su, Zuozhuo Dai, Siyu Zhu, Ping Tan
   3DV 2021 | paper | code

2. FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
   Zhiwen Fan*, Lingjie Zhu*, Honghua Li, Xiaohao Chen, Siyu Zhu, Ping Tan
   ICCV 2021 | paper | poster | video

3. Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
   Xiaodong Gu*, Zhiwen Fan*, Siyu Zhu, Zuozhuo Dai, Feitong Tan, Ping Tan
   CVPR 2020 (Oral) | paper | code | video

4. Joint CS-MRI reconstruction and segmentation with a unified deep network
   Liyan Sun*, Zhiwen Fan*, Xinghao Ding, Yue Huang, John Paisley
   IPMI 2019 | paper

5. Residual-guide network for single image deraining
   Zhiwen Fan*, Huafeng Wu*, Xueyang Fu, Yue Huang, Xinghao Ding
   ACM MM 2019 | paper

6. A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI
   Zhiwen Fan*, Liyan Sun*, Xinghao Ding, Yue Huang, Congbo Cai, John Paisley
   ECCV 2018 | paper

7. Compressed Sensing MRI Using a Recursive Dilated Network
   Liyan Sun*, Zhiwen Fan*, Yue Huang, Xinghao Ding, John Paisley
   AAAI 2018 (* equal contribution) | paper

8. Two-step approach for single underwater image enhancement
   Xueyang Fu, Zhiwen Fan, Mei Ling, Yue Huang, Xinghao Ding
   ISPACS 2017 | paper

Journal Papers:

1. A deep information sharing network for multi-contrast compressed sensing MRI reconstruction
   Liyan Sun*, Zhiwen Fan*, Xueyang Fu, Yue Huang, Xinghao Ding, John Paisley
   IEEE TIP 2019 |paper

2. Region-of-interest undersampled MRI reconstruction: A deep convolutional neural network approach
   Liyan Sun, Zhiwen Fan, Xinghao Ding, Yue Huang, John Paisley
   Magnetic resonance imaging 2019 | paper

3. A divide-and-conquer approach to compressed sensing MRI
   Liyan Sun, Zhiwen Fan, Xinghao Ding, Congbo Cai, Yue Huang, John Paisley
   Magnetic resonance imaging 2019 | paper

Awards

2019, Outstanding Graduates of Xiamen University

2017 The First Prize Scholarship of Xiamen University

2016 The First Prize Scholarship of Xiamen University

2016, Outstanding Graduates of Shandong Provience