Junhwa Hur

Hello! I am currently working as a research intern at 42dot, researching computer vision for future mobility. Previously, I worked as a Ph.D. candidate at Visual Inference group, Technische Universität Darmstadt, under the supervision of Prof. Stefan Roth Ph.D..

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo


  • 03/2021: Our paper on Multi-frame monocular scene flow has been accepted at CVPR 2021.
  • 11/2020: Chosen as one of 66 outstanding reviewers of ACCV 2020.
  • 08/2020: Chosen as one of 216 outstanding reviewers of ECCV 2020 (out of a total of 2830 reviewers).
  • 06/2020: Chosen as one of 141 outstanding reviewers of CVPR 2020 (out of a total of 3664 reviewers).
  • 02/2020: Our paper on Monocular scene flow estimation has been accepted at CVPR 2020 as an oral presentation.


I'm interested in computer vision and machine learning, especially understanding 3D dynamic scene from a monocular video through self-supervision.

Self-Supervised Multi-Frame Monocular Scene Flow

Junhwa Hur and Stefan Roth
CVPR, 2021
paper / arxiv / code

In the multi-frame setup, using ConvLSTM + warping hidden states improves the accuracy and the temporal consistency of the monocular scene flow.

Self-Supervised Monocular Scene Flow Estimation

Junhwa Hur and Stefan Roth
CVPR, 2020  Oral presentation
paper / supp / arxiv / code / talk

We propose to estimate scene flow from only two monocular images with a CNN trained in a self-supervised manner.

Optical Flow Estimation in the Deep Learning Age

Junhwa Hur and Stefan Roth
Modelling Human Motion, N. Noceti, A. Sciutti and F. Rea, Eds., Springer, 2020
paper / arxiv

As a book chapter, we comprehensively review CNN-based approaches to optical flow and their technical details, including un-/semi-supervised methods.

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

Junhwa Hur and Stefan Roth
CVPR, 2019
paper / supp / arxiv / code

Iterative residual refinement scheme based on weight sharing reduces the number of network parameters and improves the accuracy for optical flow and occlusion.

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

Simon Meister, Junhwa Hur and Stefan Roth
AAAI, 2018  Oral presentation
paper / arxiv / code / slide

Directly training on the target domain with a better unsupervised loss can outperform the supervised pre-training on synthetic dataset.

MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation

Junhwa Hur and Stefan Roth
ICCV, 2017
paper / supp / arxiv / code / poster

The chicken-and-egg relationship between optical flow and occlusion can be nicely formulated through exploiting the symmetry properties they have.

Joint Optical Flow and Temporally Consistent Semantic Segmentation

Junhwa Hur and Stefan Roth
ECCV Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving (ECCVW), 2016  Best paper award
paper / arxiv / poster

Optical flow and semantic segmentation can mutually leverage each other.

Generalized Deformable Spatial Pyramid: Geometry-Preserving Dense Correspondence Estimation

Junhwa Hur, Hwasup Lim, Changsoo Park, and Sang Chul Ahn
CVPR, 2015
paper / supp / project / video

Piece-wise similarity transform through pyramid levels can handle non-rigid deformation in semantic matching.

3D Deformable Spatial Pyramid for Dense 3D Motion Flow of Deformable Object

Junhwa Hur, Hwasup Lim, and Sang Chul Ahn
International Symposium on Visual Computing (ISVC), 2014  Oral presentation
paper / project

Multi-lane Detection based on Accurate Geometric Lane Estimation in Highway Scenarios

Seung-Nam Kang, Soo-Mok Lee, Junhwa Hur, and Seung-Woo Seo
Intelligent Vehicles Symposium (IV), 2014
paper / video

Multi-lane Detection in Urban Driving Environments using Conditional Random Fields

Junhwa Hur, Seung-Nam Kang, and Seung-Woo Seo
Intelligent Vehicles Symposium (IV), 2013
paper / project / code / video

Multi-lane Detection in Highway and Urban Driving Environment

Junhwa Hur
Master’s thesis, Seoul National University, 2013
paper / project


Deformable Object Modeling

IMRC, Korea Institute of Science and Technology (KIST), 2015

Researching on modeling deformable object: pose estimation, correspondence search, and loop closure

Korea Autonomous Vehicle Contest 2013

VILab, Seoul National University, 2013   2nd-place prize
video / project

Researching on computer vision system for autonomous driving: lane/speed-bump/stop-line detection, camera-lidar sensor fusion

Design / source code from Jon Barron's / Leonid Keselman's website