Research
My research interests lie at the intersection of computer vision and graphics, including neural rendering, inverse rendering and 3D reconstruction.
Previously, I worked on developing recommender systems methods.
|
Publications
* indicates equal contribution
|
|
Neural Repeated Texture Field (NeRTF): Learning Continuous Implicit Representation for Near-Periodic Patterns.
Bowei Chen,
Tiancheng Zhi,
Martial Hebert,
Srinivasa Narasimhan.
(Under Review)
Present a single image based framework to learn Near-Periodic Patterns (NPP) representation, which is adapted to various applications including completion, resolution-enhanced remapping, and segmentation.
|
|
Semantically Supervised Appearance Decomposition for Virtual Staging from a Single Panorama.
Tiancheng Zhi,
Bowei Chen,
Ivaylo Boyadzhiev,
Sing Bing Kang,
Martial Hebert,
Srinivasa Narasimhan.
ACM Transactions on Graphics, SIGGRAPH 2022
[Paper]
[Website]
[Code]
Present a weakly supervised appearance decomposition for a single indoor panorama. The applications include furniture insertion, sunlight direction changing, and floor material changing.
|
|
Leveraging Title-Abstract Attentive Semantics for Paper Recommendation
Guibing Guo,
Bowei Chen,
Xiaoyan Zhang,
Zhirong Liu,
Zhenhua Dong,
Xiuqiang He.
The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020
[paper]
Propose a two-level attentive neural network to capture title-abstract semantics relationships for paper recommendation.
|
|