Publications

for the full publication list, please see Google Scholar
(patents excluded).

Papers

CLRerNet: Improving Confidence of Lane Detection with LaneIoU
Hiroto Honda, Yusuke Uchida
[Paper] [Code] Accepted to WACV2024.
SOTA on CULane lane detection benchmark as of July 2024.

End-to-End Monocular Vanishing Point Detection Exploiting Lane Annotations
Hiroto Honda, Motoki Kimura, Takumi Karasawa, Yusuke Uchida
[Paper] arXiv, 2021.

Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video
Naoki Kato, Hiroto Honda, Yusuke Uchida
[Paper] GCCE, 2020.

Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, Yusuke Uchida
[Paper] ECCVW, 2018.

Make My Day - High-Fidelity Color Denoising with Near-Infrared
Hiroto Honda, Radu Timofte, Luc Van Gool
[Paper] CVPRW, pp.82-90, 2015.

Presentations

Digging into Sample Assignment Methods for Object Detection
Hiroto Honda,
[Slides]

Tackling Open Images Challenge
Hiroto Honda,
[Slides in English] [Slides in Japanese]
lunch workshop, the 26th Symposium on Sensing via Image Information (2020).

Competition Solutions

The 6th Place Solution for the Open Images 2019 Object Detection Track
Hiroto Honda (Schwert)
[Poster] [Kaggle Discussion]
above poster presented at ICCVW, 2019.

The 11th Place Solution for the Open Images 2019 Instance Segmentation Track
Hiroto Honda (Schwert)
[Kaggle Discussion]