Robotics and Computer Vision Lab

Publications

조회 수 283 댓글 0
Extra Form
저 자 Namil Kim, Yukyung Choi, Soonmin Hwang, In So Kweon
학 회 Association for the Advancement of Artificial Intelligence (AAAI)
Notes This work was supported by the Development of Autonomous Emergency Braking System for Pedestrian Protection project funded by the Ministry of Trade, Industry and Energy of Korea (MOTIE)(No.10044775). We also supported to gold prize from 23th HumanTech Paper Award in Samsung.
논문일시(Year) 2018
논문일시(Month) 02
http://multispectral.kaist.ac.kr** The first and second authors contributed equally to this work.

To understand the real-world, it is essential to perceive in all-day conditions including cases which are not suitable for RGB sensors, especially at night. Beyond these limitations, the innovation introduced here is a multispectral solution in the form of depth estimation from an illumination- invariant thermal sensor without an additional depth sensor. Based on an analysis of multispectral properties and the relevance to depth predictions, we propose an efficient and novel multi-task framework called the Multispectral Transfer Net- work (MTN) to estimate a depth image from a single thermal image. By exploiting geometric priors and chromaticity clues, our model can generate a pixel-wise depth image in an unsupervised manner. Moreover, we propose a new type of multitask module called Interleaver as a means of incorporating the chromaticity and fine details of skip-connections into the depth estimation framework without sharing feature layers. Lastly, we explain a novel technical means of stably training and covering large disparities and extending thermal images to data-driven methods for all-day conditions. In experiments, we demonstrate the better performance and generalization of depth estimation through the proposed multispectral stereo dataset, including various driving conditions.

List of Articles
291. Learning Image Representations by Completing Damaged Jigsaw Puzzles
Dahun Kim , Donghyeon Cho , Donggeun Yoo , In So Kweon
IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 / 05
290. StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
Sanghyun Woo, Soonmin Hwang, In So Kweon
IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 / 03
» Multispectral Transfer Network: Unsupervised Depth Estimation for All-day Vision
Namil Kim, Yukyung Choi, Soonmin Hwang, In So Kweon
Association for the Advancement of Artificial Intelligence (AAAI) 2018 / 02
288. Co-domain Embedding using Deep Quadruplet Network for Unseen Traffic Sign Recognition
Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
Association for the Advancement of Artificial Intelligence (AAAI) 2018 / 02
287. Intelligent Assistant for People with Low Vision Abilities
Oleksandr Bogdan, Oleg Yurchenko, Oleksandr Bailo, Francois Rameau, Donggeun Yoo, In So Kweon
The 8th Pacific Rim Symposium on Image and Video Technology (PSIVT) 2017 / 11
286. VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition
Seokju Lee, Junsik Kim, Jae Shin Yoon, Seunghak Shin, Oleksandr Bailo, Namil Kim, Tae-Hee Lee, Hyun Seok Hong, Seung-Hoon Han, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2017 / 10
285. Two-Phase Learning for Weakly Supervised Object Localization
Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2017 / 10
284. Weakly- and Self- Supervised Learning for Content-Aware Deep Image Retargeting
Donghyeon Cho, Jinsun Park, Tae-Hyun Oh, Yu-Wing Tai, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2017 / 10
283. Deltille Grids for Geometric Camera Calibration
Hyowon Ha, Michal Perdoch, Hatem Alismail, In So Kweon, Yaser Sheikh
IEEE International Conference on Computer Vision (ICCV) 2017 / 10
282. Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning
Tae-Hyun Oh, Kyungdon Joo, Neel Joshi, Baoyuan Wang, In So Kweon, Sing Bing Kang
IEEE International Conference on Computer Vision (ICCV) 2017 / 10
281. Noise Robust Depth From Focus Using a Ring Difference Filter
Jaeheung Surh, Hae-Gon Jeon, Yunwon Park, Sunghoon Im, Hyowon Ha, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 / 07
280. Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks
Jae Shin Yoon, Francois Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2017 / 10
279. A Real-Time and Energy-Efficient Embedded System for Intelligent ADAS with RNN-Based Deep Risk Prediction using Stereo Camera
Kyuho Lee, Gyeongmin Choe, Kyeongryeol Bong, Changhyeon Kim, In So Kweon, Hoi-Jun Yoo
International Conference on Computer Vision Systems (ICVS) 2017 / 07
278. A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation
Jinsun Park, Yu-Wing Tai, Donghyeon Cho, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 / 07
277. Deep Representation of Industrial Components using Simulated Images
Seong-Heum Kim, Gyeongmin Choe, Byungtae Ahn, In So Kweon
IEEE International Conference on Robotics and Automation (ICRA) 2017 / 05
276. Single Image Depth Estimation using Convolutional Neural Networks with NCC-based Loss
Jinsun Park, In So Kweon
International Workshop on Frontiers of Computer Vision (FCV) 2017 / 02
275. Robust Road Marking Detection and Recognition Using Density-Based Grouping and Machine Learning Techniques
Oleksandr Bailo, Seokju Lee, Francois Rameau, Jae Shin Yoon, In So Kweon
Winter Conference of Applications on Computer Vision (WACV) 2017 / 03
274. Control strategies for a humanoid robot to drive and then egress a utility vehicle for remote approach
Hyobin Jeong, Jaesung Oh, Mingeuk Kim, Kyungdon Joo, In So Kweon, Jun-Ho Oh
IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) 2015 / 11
273. A Real-time Vehicular Vision System to Seamlessly See-through Cars
Francois Rameau, Hyowon Ha, Kyungdon Joo, Jinsoo Choi, In So Kweon
European Conference on Computer Vision Workshops (ECCVW - ACVR) 2016 / 10
272. A Real-time Augmented Reality System to See-Through Cars
Francois Rameau, Hyowon Ha, Kyungdon Joo, Jinsoo Choi, Kibaek Park, In So Kweon
IEEE International Symposium on Mixed and Augmented Reality (ISMAR) 2016 / 09
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 16 Next
/ 16