Video Processing
Low-level video enhancement
- Frame Interpolation
- Super-Resolution
- Stabilization
- Compression
Vision and Video Dynamics Lab
We study how the visual world changes over time — and build systems that perceive, reconstruct, and predict that change.
From pixel-level motion to world-scale simulation, ViViD Lab pursues a single research agenda — temporal dynamics — at increasing levels of abstraction.
Video Understanding
Temporal semantics & representation
- Video Foundation Models
- Action Recognition
- Retrieval & QA
3D / 4D Vision
3D scene reconstruction & rendering
- NeRF
- Gaussian Splatting
- Novel View Synthesis
World Models
Generative simulation of the visual world
- World Foundation Models
- Action-Conditioned Video Generation
- Physics-Aware Generation
- Embodied AI
We're actively looking for new lab members — MS, PhD, and undergraduate interns.
If our research speaks to you and you're curious about how machines perceive time, motion, and change, we'd love to hear from you. We care more about curiosity and persistence than any specific background.
News
All news → 2026
- Paper
Probing Intrinsic Bias: Internal Attention Feature Analysis for Social Bias Evaluation in Diffusion Models accepted to Neurocomputing.
- Lab
ViViD Lab officially launches at SeoulTech. Welcome!
2025
- Paper
Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting accepted to NeurIPS 2025.
2023
- Paper
Exploring Discontinuity for Video Frame Interpolation accepted to CVPR 2023 (Highlight, top 10%).