Woobin Im

About

I am currently at Samsung Electronics within the Neural Graphics Unit (Mobile and S.LSI Divisions), specializing in real-time neural graphics with a primary focus on frame generation. Most recently, I have been actively involved in the development of ENSS (Exynos Neural Super Sampling) for AI-driven game boosting. Before this, my research was about using machine learning to solve computer vision problems, especially those related to motion and video. I've stayed on that path, now pushing this technology forward in real-time graphics applications.

Research interests: graphics, video, optical flow, NeRF

Award

• Naver Ph.D Fellowship Award, 2022.
• Finalist at Qualcomm Innovation Fellowship Korea (QIFK), 2020.
• Outstanding Teaching Assistant Award (우수조교상), KAIST, 2019.

Education

• KAIST, Ph.D., Computer Science2018-2024
  • Advisor: Professor Sung-Eui Yoon
• KAIST, M.S., Computer Science2016-2018
  • Advisor: Professor Hyun Seung Yang
• Yonsei University, B.S., Computer Science2012-2016

Work

• Mobile eXperience, Samsung Electronics2026.01-current
• System LSI, Samsung Electronics2025.06-2026.01
• Samsung Advanced Institute of Technology (SAIT)Samsung Electronics2024.08-2025.06
• CLOVA, NAVER Cloud Corp. (internship)2023.02-2023.08

Projects

• Mobile Neural Frame Generation (Skill: Unreal Engine, C++, Vulkan)2025-current
• SGVR KAIST Website (Skill: web frontend, Wordpress, PHP)2018-2024
• GPU Cluster (Skill: Docker, Kubernetes, Grafana)2023-2024

Publication

• Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering
  Sebin Lee Jumin Lee Taeyeon Kim Youngju Na Woobin Im Sung-Eui Yoon
  Conference on Computer Vision and Pattern Recognition (CVPR)
  [to appear]
• Regularizing Dynamic Radiance Fields with Kinematic Fields
  Woobin Im Geonho Cha Sebin Lee Juhyeong Seon Jumin Lee Dongyoon Wee Sung-Eui Yoon
  European Conference on Computer Vision (ECCV)
  [arxiv]
• Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
  Xu Yin Woobin Im Dongbo Min Yuchi Huo Fei Pan Sung-Eui Yoon
  IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  [arxiv] [web] [github]
• Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation
  Juhyeong Seon Woobin Im Sebin Lee Jumin Lee Sung-Eui Yoon
  International Conference on Image Processing (ICIP)
  [arxiv] [github]
• SemCity: Semantic Scene Generation with Triplane Diffusion
  Jumin Lee Sebin Lee Changho Jo Woobin Im Ju-hyeong Seon Sung-Eui Yoon
  Conference on Computer Vision and Pattern Recognition (CVPR)
  *Equal contribution [arxiv] [web] [github]
• Multi-resolution distillation for self-supervised monocular depth estimation
  Sebin Lee Woobin Im Sung-Eui Yoon
  Pattern Recognition Letters
• Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data
  Jumin Lee Woobin Im Sebin Lee Sung-Eui Yoon
  Workshop on Image Processing and Image Understanding (IPIU)
  Best Paper Award [arxiv] [github]
• Scenario Generation by Action Scene-Graph Prediction
  Woobin Im Woo Jae Kim Sung-Eui Yoon
  Korea Software Congress (KSC)
  [web] [paper]
• Semi-Supervised Learning of Optical Flow by Flow Supervisor
  Woobin Im Sebin Lee Sung-Eui Yoon
  European Conference on Computer Vision (ECCV)
  [web] [arxiv] [github]
• In-N-Out: Towards Good Initialization for Inpainting and Outpainting
  Changho Jo Woobin Im Sung-Eui Yoon
  British Machine Vision Conference (BMVC)
  [web] [arxiv] [github]
• Self-Supervised Visual Odometry via Frame Interpolation
  Sebin Lee Woobin Im Sung-Eui Yoon
  Korea Robotics Society Annual Conference (KRoC)
  [paper]
• Unsupervised Learning of Optical Flow with Deep Feature Similarity
  Woobin Im Tae-Kyun Kim Sung-Eui Yoon
  European Conference on Computer Vision (ECCV)
  [web] [paper] [github]
• Combined Center Dispersion Loss Function for Deep Facial Expression Recognition
  Abhilasha Nanda Woobin Im Key-Sun Choi Hyun Seung Yang
  Pattern Recognition Letters
  [paper]
• Two-stream Spatiotemporal Feature for Video QA Task
  Chiwan Song Woobin Im Sung-Eui Yoon
  https://arxiv.org/abs/1907.05006
  [arxiv]
• Acoustic Material Estimation with Convolutional Neural Network
  Doheon Lee Inkyu An Woobin Im Sung-Eui Yoon
  Korea Robotics Society Annual Conference (KRoC)
  [paper]
• An Application of Convolutional-LSTM Network and Video QA
  Chiwan Song Woobin Im Sung-Eui Yoon
  Korea Computer Congress (KCC)
  [paper]
• Scale-Varying Triplet Ranking with Classification Loss for Facial Age Estimation
  Woobin Im Sungeun Hong Sung-Eui Yoon Hyun S. Yang
  Asian Conference on Computer Vision (ACCV)
  [web] [paper] [github]
• CBVMR: Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint
  Sungeun Hong Woobin Im Hyun S. Yang
  Proceedings of the ACM international conference on Multimedia Retrieval (ICMR)
  [paper] [video]
• D3: Recognizing dynamic scenes with deep dual descriptor based on key frames and key segments
  Sungeun Hong Jongbin Ryu Woobin Im Hyun S. Yang
  Neurocomputing
  [paper]
• SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
  Sungeun Hong Woobin Im Jongbin Ryu Hyun S. Yang
  International Conference on Image Processing (ICIP'17), IEEE
  Oral [paper]
• Convolutional Texture Networks based on Histogram Pooling
  Jongbin Ryu Sungeun Hong Woobin Im Hyun S. Yang
• Image-text multi-modal representation learning by adversarial backpropagation
  Gwangbeen Park Woobin Im
  arXiv preprint arXiv:1612.08354
• Deep CNN-based Person Identification using Facial and Clothing Features
  Sungeun Hong Woobin Im Junwoo Park Hyun S. Yang
  Jun 2016, Summer General Conference '16, IEEK

Patent

• 트리플릿 기반의 손실함수를 활용한 순서가 있는 분류문제를 위한 딥러닝 모델 학습 방법 및 장치 (Using Triplet-based Loss for Training Ordinal Classification Deep Models)
  [US App] [KR App]
• 부분 이미지 기반 객체 판별 방법 및 장치 (Partial Face Based Person Identification Across Poses)
  [KR]
• 도메인 적응 기반 객체 인식 모델 제공 장치 및 방법 (APPARATUS AND METHOD FOR PROVIDING OBJECT RECOGNITION MODEL BASED ON DOMAIN ADAPTATION)
  [KR App]
• 광학 흐름 추정을 위한 딥 유사도 기반 비지도 학습의 컴퓨터 시스템 및 그의 방법 (COMPUTER SYSTEM OF UNSUPERVISED LEARNING WITH DEEP SIMILARITY FOR OPTICAL FLOW ESTIMATION AND METHOD THEREOF)
  [KR] [US App]

Experience

• Teaching Assistants
  • GSAG-KAIST Research and Education Program, 1/2019-2/2019
  • CS206: Data Structure (Spring 2019), 3/2019-6/2019
  • CS688: Web-Scale Image Retrieval (Fall 2018), 9/2018-12/2018
  • CS101: Introduction to Programming, 9/2016-12/2017, 9/2018-12/2018
• Undergraduate Research Assistant
  • DB Lab, Yonsei University, 1/2014-2/2014