Yongjie Zhu

I am now an Algorithm Engineer at Alibaba Group (Beijing). I obtained my Master degree from School of Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT), co-supervised by Prof. Si Li and Prof. Boxin Shi.

I was a research intern at Microsoft, where I work on computer vision and natural language processing. I also worked as a research intern at Tencent, WXG. At Tencent I've worked on 3D Human Body Estimation and Face Appearance Modeling under the guidance of Dr. Chen Li. Before that, I got my Bachelor degree at BUPT, advised by Prof. Si Li. I've received the China National Scholarship and the JJWorld (Beijing) Network Technology Scholarship (top 3%) at BUPT.

Email  /  CV  /  Bio  /  Google Scholar  /  LinkedIn  /  Github

• [2023.10] One paper accepted to TPAMI 2023.
• [2023.02] One paper accepted to CVPR 2023.
• [2022.11] Excellent graduation thesis of BUPT.
• [2022.07] One oral paper accepted to ECCV 2022.
• [2022.06] AdsCVLR is accepted by ACM MM 2022.
---- show more ----
[2021.11] Received China National Scholarship.
[2021.05] Outstanding reviewer of CVPR 2021.
[2021.05] The extension of my bachelor thesis HyFRIS-Net got accepted by TPAMI 2021!
[2021.03] SOLID-Net is accepted by CVPR 2021 as oral presentation (top 4%)!
[2021.03] DeRenderNet is accepted by ICCP 2021.

My research interests lie at the intersection of computer vision, computer graphics, and computational photography. Recently, I focus on physics-based computer vision and multimodal in natural language processing, including inferring the physical world (shape, color, light, etc) and linguistic text from images. Representative papers are highlighted.

This paper proposes a novel pipeline to estimate a non-parametric environment map with high dynamic range from a single human face image.

This paper proposes to complement the intrinsic estimation from volume rendering using NeRF and from inversing the photometric image formation model using convolutional neural networks (CNNs).

Given a single image and a 2D pixel location, our method can estimate the local lighting that is disentangled into ambient sky light, sun light and lighting-independent local contents.

We propose a multi-modal relevance modeling approach for sponsored search, and boost the performance via contrastive learning that naturally extends the transformer encoder with the complementary multi-modal inputs.

We proposed a self-supervised deep learning framework that can estimate the hybrid reflection model and detailed normal of the human face. The proposed hybrid reflectance and illumination representation ensures the photo-realistic face reconstruction.

Collecting high quality paired intrinsic and lighting data in a virtual city lets you train a model that estimates spatially-varying lighting from a single outdoor image.

Decomposing a single RGB image into its reflectance, shading (caused by direct lighting), and shadow (caused by occlusion) images.

Homepage of Yongjie Zhu [朱勇杰]
© Yongjie Zhu. All Rights Reserved.