Robotics and Computer Vision Lab

Publications

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
379. ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation
Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim, In So Kweon
European Conference on Computer Vision (ECCV) 2022 / 10
378. A Unified Learning Framework for Large Vocabulary Video Object Detection
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee
European Conference on Computer Vision (ECCV) 2022 / 10
377. Tracking by Associating Clips
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee
European Conference on Computer Vision (ECCV) 2022 / 10
376. The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing
Dawit Mureja Argaw, Fabian Caba Heilbron, Markus Woodson, Joon-Young Lee, In So Kweon
European Conference on Computer Vision 2022 / 10
375. DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning
Ukcheol Shin, Kyunghyun Lee, In So Kweon
International Conference on Intelligent Robots and Systems (IROS) 2022 / 06
374. Investigating Top-k White-Box and Transferable Black-box Attack
Chaoning Zhang, Philip Benz, Adil Karjauv, JaeWon Cho, Kang Zhang, In So Kweon
Computer Vision and Pattern Recognition, CVPR 2022 / 03
373. DASO: Distribution-Aware Semantics-Oriented Pseudo-Label for Imbalanced Semi-Supervised Learning
Youngtaek Oh, Dong-Jin Kim, and In So Kweon
Computer Vision and Pattern Recognition, CVPR 2022 / 03
372. Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo
Chaoning Zhang*, Kang Zhang,∗, Trung X. Pham,∗, Axi Niu, Zhinan Qiao Chang D. Yoo, In So Kweon
Computer Vision and Pattern Recognition, CVPR 2022 / 03
371. TubeFormer-DeepLab: Video Mask Transformer
Dahun Kim, Jun Xie, Huiyu Wang, Siyuan Qiao, Qihang Yu, Hong-Seok Kim,Hartwig Adam, In So Kweon, Liang-Chieh Chen
Computer Vision and Pattern Recognition, CVPR 2022 / 03
370. Per-Clip Video Object Segmentation
Kwanyong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee
Computer Vision and Pattern Recognition, CVPR 2022 / 03
369. MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
Inkyu Shin, Yi-Hsuan Tsai, Samuel Schulter, Bingbing Zhuang, Buyu Liu, Sparsh Garg, In So Kweon, Kuk-Jin Yoon
Computer Vision and Pattern Recognition, CVPR 2022 / 03
368. Restoration of Video Frames from a Single Blurred Image with Motion Understanding
Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Chaoning Zhang, In So Kweon
Computer Vision and Pattern Recognition Workshop, CVPRW 2022 / 03
367. Long-term Video Frame Interpolation via Feature Propagation
Dawit Mureja Argaw, In So Kweon
Computer Vision and Pattern Recognition, CVPR 2022 / 03
366. UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon, Kuk-Jin Yoon
Computer Vision and Pattern Recognition, CVPR 2022 / 03
365. Learning Sound Localization Better from Semantically Similar Samples
Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, In So Kweon
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022 / 5
364. PointRecon: Deep Point Cloud Reconstruction
Jaesung Choe*, Byeonin Joung*, Francois Rameau, Jaesik Park, and In So Kweon
International Conference on Learning Representations (ICLR) 2022/04 /
363. Single-Modal Entropy based Active Learning for Visual Question Answering
Dong-Jin Kim*, Jae Won Cho*, Jinsoo Choi, Yunjae Jung, In So Kweon (*Equal Contribution)
British Machine Vision Conference (BMVC) 2021 / 11
362. Less Can Be More: Sound Source Localization With a Classification Model
Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV) 2022 / 1
361. Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective
Philipp Benz*, Chaoning Zhang*, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2021 / 10
360. Data-Free Universal Adversarial Perturbation and Black-Box Attack
Chaoning Zhang*, Philipp Benz*, Adil Karjauv*, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2021 / 10
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 20 Next
/ 20