Posts by Collection

portfolio

publications

Generating Diverse and Descriptive Image Captions Using Visual Paraphrases

Published in ICCV, 2019

This paper improves the diversity and descriptiveness of machine-generated image captions by utilizing visual paragraphs in existing captioning datasets.

Recommended citation: Lixin Liu, Jiajun Tang, Xiaojun Wan, and Zongming Guo. "Generating Diverse and Descriptive Image Captions Using Visual Paraphrases." ICCV, 2019.

DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering

Published in ICCP, 2021

This paper propose a method to decompose the shadow-free albedo and latent lighting, and render shape-(in)dependent shadings, given a single image of an outdoor urban scene, trained in a self-supervised manner.

Recommended citation: Yongjie Zhu, Jiajun Tang, Si Li, and Boxin Shi. "DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering." ICCP, 2021.

L-CoDe: Language-based Colorization using Color-object Decoupled Conditions

Published in AAAI, 2022

This paper propose a language-guided grey image colorization method which handles the color-object coupling and mismatch issues.

Recommended citation: Shuchen Weng, Hao Wu, Zheng Chang, Jiajun Tang, Si Li, and Boxin Shi. "L-CoDe: Language-based Colorization using Color-object Decoupled Conditions." AAAI, 2022.

Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation

Published in ECCV, 2022

This paper presents a novel disentangled and editable lighting representation for spatially-varying outdoor lighting with few parameters, which can be used for outdoor spatially-varying lighting estimation task.

Recommended citation: Jiajun Tang, Yongjie Zhu, Haoyu Wang, Jun Hoong Chan, Si Li, and Boxin Shi. "Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation." ECCV, 2022.

Complementary Intrinsics from Neural Radiance Fields and CNNs for Outdoor Scene Relighting

Published in CVPR, 2023

This paper presents a novel outdoor scene relighting method combining advantages of both NeRF-based methods and CNN-based methods.

Recommended citation: Siqi Yang, Xuanning Cui, Yongjie Zhu, Jiajun Tang, Si Li, Zhaofei Yu, and Boxin Shi. "Complementary Intrinsics from Neural Radiance Fields and CNNs for Outdoor Scene Relighting." CVPR, 2023.

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.