Minhyeok Lee

Postdoctoral Researcher

Image and Video Pattern Recognition Lab, Yonsei University

prof_pic.jpg

I am a Postdoctoral Researcher at the Image and Video Pattern Recognition Lab, Yonsei University, where I also completed my Integrated M.S./Ph.D. in Electrical and Electronic Engineering in Feb. 2026.

My research focuses on:

Vision-Language Models Pixel-Level Generative & Understanding Models 3D Novel View Synthesis Autonomous Driving

To know more about me, please check out my CV or visit my Github.

news

  1. New
    🌉 Presented at ECCV 2026, Malmö, Sweden
    • [ECCV 2026] Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning
  2. 🏔️ Presented at CVPR 2026, Denver, Colorado, USA.
    • [CVPR Findings 2026] SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
    • [CVPR Findings 2026] Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting
  3. 📘 Accepted to Pattern Recognition (2026)
    • [PR 2025] Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation
  4. 🦁 Presented at AAAI 2026, Singapore.
    • [AAAI 2026] MonoCLUE: Object-aware Clustering Enhances Monocular 3D Object Detection
  5. 🌊 Presented at NeurIPS 2025, San Diego, California, USA.
    • [NeurIPS 2025] Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
  6. 🏝️ Presented at ICCV 2025, Honolulu, Hawaii, USA.
    • [ICCV 2025] CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images
  7. 🎸 Presented at CVPR 2025, Nashville, Tennessee, USA.
    • [CVPR 2025] Effective SAM Combination for Open-Vocabulary Semantic Segmentation - Oral presentation!
    • [CVPR 2025] CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
  8. 📘 Accepted to IEEE TPAMI (2025)
    • [TPAMI 2025] Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse View
  9. 🔔 Presented at AAAI 2025, Philadelphia, Pennsylvania, USA.
    • [AAAI 2025] Video Diffusion Models are Strong Video Inpainter
  10. ☕ Presented at CVPR 2024, Seattle, USA.
    • [CVPR 2024] Guided Slot Attention for Unsupervised Video Object Segmentation
    • [CVPR 2024] Dual Prototype Attention for Unsupervised Video Object Segmentation
  11. 🗼 Presented at ICCV 2023, Paris, France.
    • [ICCV 2023] Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
    • [ICCV 2023] Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
  12. 🍁 Presented at CVPR 2023, Vancouver, Canada.
    • [CVPR 2023] DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors
  13. 🏝️ Presented at WACV 2023, Waikoloa, Hawaii, USA.
    • [WACV 2023] Unsupervised Video Object Segmentation via Prototype Memory Network
    • [WACV 2023] Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
  14. 🕍 Presented at ECCV 2022, Tel Aviv, Israel.
    • [ECCV 2022] Superpixel Prototype Sampling Network for RGB-D Salient Object Detection
    • [ECCV 2022] Tackling Background Distraction in Video Object Segmentation
  15. 🏝️ Presented at WACV 2022, Waikoloa, Hawaii, USA.
    • [WACV 2022] Robust Lane Detection via Expanded Self-Attention
    • [WACV 2022] Edgeconv with attention module for monocular depth estimation
    • [WACV 2022] FastAno: Fast Anomaly Detection via Spatio-Temporal Patch Transformation
  16. 🌐 Presented at CVPR 2021 (Virtual).
    • [CVPR 2021] Regularization Strategy for Point Cloud via Rigidly Mixed Samples