BYeongjun park (박병준)
Tel: +82-42-350-7521
E-Mail: pbj3810[at]kaist.ac.kr
Education
2020.3 - Present Combined M.S./ Ph.D. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea
2015.3 - 2020.2 B.S. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea
Research Interests
Deep Learning
3D Vision
Novel View Synthesis
Projects
2020.08 ~ 2021.08
Samsung Advanced Institude of Technology (SAIT) - Monocular Scene Flow estimation
2020.09 ~ 2022.02
Ministry of Science and ICT (MSIT) - Anthropocene Study (digital ecology with AI)
Publications
Byeongjun Park and Changick Kim, "Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Video," in Proc. the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Hawaii, USA, Jan. 4-6, 2024.
Byeongjun Park*, Hyojun Go*, and Changick Kim, "Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis", Submitted to IEEE Transaction of Pattern Analysis and Machine Intelligence (TPAMI), Nov. 2022. (* These two authors contributed equally)
Jeongsoo Kim, Sangmin Woo, Byeongjun Park, and Changick Kim, "TEMPORAL FLOW MASK ATTENTION FOR OPEN-SET LONG-TAILED RECOGNITION OF WILD ANIMALS IN CAMERA-TRAP IMAGES", in Proc. the 29th IEEE International Conference on Image Processing (ICIP), Bordeaux, France, Oct. 16-19, 2022.
Hyojun Go, Junyoung Byun, Byeongjun Park, M. Choi, S. Yoo, and Changick Kim, “Fine-Grained Multi-Class Object Counting,” in Proc. the 28th IEEE International Conference on Image Processing (ICIP), Anchorage, Alaska, USA, Sep. 19-22, 2021.
김정수, 박병준, 조승주, 최명애, 박진영, 서형수, 김창익, "트랩 카메라 영상 데이터셋을 활용한 옵티컬 플로우 퓨전 딥러닝 네트워크," 대한전자공학회 추계학술대회, 송도컨벤시아 인천, Nov. 26-27, 2021.
고효준, 박병준, 김창익, "적대적인 공격에 대한 인증 가능한 방어 방법의 성능 향상", 한국방송미디어공학회 추계학술대회, 온라인, Nov. 27-28, 2020.
박병준, 고효준, 김창익, "단계별 비용 체적 정규화를 이용한 자기 지도 학습 기반 단안 씬(Scene) 플로우 추정", 대한전자공학회 추계학술대회, 김대중컨벤션센터 (광주광역시), Nov. 27-28, 2020.
Patents
Youngjun Kwak, Taekyung Kim, Changick Kim, Byeongjun Park, and C. Park, "Method and apparatus with scene flow estimation" (US20220301190A1), Sep. 2022.