3 papers
cs.CV2025
Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes
JunYong Choi, Min-Cheol Sagong, SeokYeong Lee +3
We propose a diffusion-based inverse rendering framework that decomposes a single RGB image into geometry, material, and lighting. Inverse rendering is inherently ill-posed, making…
cs.CV2025
VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition
Minsoo Kim, Min-Cheol Sagong, Gi Pyo Nam +2
Deep learning-based face recognition continues to face challenges due to its reliance on huge datasets obtained from web crawling, which can be costly to gather and raise significa…
cs.CV2024
Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset
Sithu Aung, Min-Cheol Sagong, Junghyun Cho
We address an advanced challenge of predicting pedestrian occupancy as an extension of multi-view pedestrian detection in urban traffic. To support this, we have created a new synt…