Boyi Li

Boyi Li

Auto-generated profile, based on publicly available information

Boyi Li

NVIDIA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 August 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
BLBoyi Li
Boyi Li
Wenqi RenWenqi Ren
Wenqi Ren
DFDengpan Fu
Dengpan Fu
DTDacheng Tao
Dacheng Tao
DFDan Feng
Dan Feng
ZWZhangyang (Atlas) Wang
Zhangyang (Atlas) Wang
We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics to no-reference metrics and to subjective evaluation, and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of the state-of-the-art dehazing algorithms, and suggest promising future directions.

1 October 2026 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ZLZhixuan Liang
Zhixuan Liang
YCYuxiao Chen
Yuxiao Chen
YYYurong You
Yurong You
PKPeter Karkus
Peter Karkus
WDWenhao Ding
Wenhao Ding
MPMarco Pavone
Marco Pavone

15 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
BLBoyi Li
Boyi Li
YCYin Cui
Yin Cui
TLTsung-Yi Lin
Tsung-Yi Lin
SBSerge Belongie
Serge Belongie
Recent advances in data augmentation enable one to translate images by learning the mapping between a source domain and a target domain. Existing methods tend to learn the distributions by training a model on a variety of datasets, with results evaluated largely in a subjective manner. Relatively few works in this area, however, study the potential use of image synthesis methods for recognition tasks. In this paper, we propose and explore the problem of image translation for data augmentation. We first propose a lightweight yet efficient model for translating texture to augment images based on a single input of source texture, allowing for fast training and testing, referred to as Single Image Texture Translation for data Augmentation (SITTA). Then we explore the use of augmented data in long-tailed and few-shot image classification tasks. We find the proposed augmentation method and workflow is capable of translating the texture of input data into a target domain, leading to consistently improved image recognition performance. Finally, we examine how SITTA and related image translation methods can provide a basis for a data-efficient, "augmentation engineering" approach to model training. Codes are available at https://github.com/Boyiliee/SITTA.