Heeseong Shin

prof_pic.jpg

I am curently a Ph.D student at the CVLAB at KAIST AI, advised by Seungryong Kim. My main research interest lies in solving practical tasks, such as image segmentation and 3D reconstruction, in an efficient manner by leveraging foundation models. I am also interested in diffusion models and Vision-Language Models (VLMs).

I had the opportunity to intern at Naver AI Lab, where I worked with Taekyung Kim. I have also collaborated with Google Research and Microsoft Research Asia, and I am continuing to work closely with Anurag Arnab at Google Deepmind.

Outside of research, I am a huge fan of the Scuderia in Formula 1 and I also love to travel. If you are interested in my work, please feel free to reach out to me!

publications

(*) denotes equal contribution
  1. ICCV
    S4M: Boosting Semi-Supervised Instance Segmentation with SAM
    Heeji Yoon*, Heeseong Shin*, Eunbeen Hong, Hyunwook Choi, Hansang Cho, Daun Jeong, and Seungryong Kim
    In IEEE/CVF International Conference on Computer Vision, 2025
  2. ICML
    PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis
    Sunghwan Hong*, Jaewoo Jung*, Heeseong Shin, Jisang Han, Jiaolong Yang, Chong Luo, and Seungryong Kim
    In International Conference on Machine Learning, 2025
  3. NeurIPS
    Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
    Heeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab†, Paul Hongsuck Seo†, and Seungryong Kim†
    In Advances in Neural Information Processing Systems, 2024
  4. ICMLW
    Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
    Susung Hong, Junyoung Seo, Heeseong Shin, Sunghwan Hong, and Seungryong Kim
    In First Workshop on Controllable Video Generation at ICML, 2024
  5. CVPR Highlight
    CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
    Seokju Cho*, Heeseong Shin*, Sunghwan Hong, Anurag Arnab, Paul Hongsuck Seo, and Seungryong Kim
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
  6. CVPR Highlight
    Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis
    Sunghwan Hong, Jaewoo Jung, Heeseong Shin, Jiaolong Yang, Seungryong Kim, and Chong Luo
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024