3 papers
cs.CV2026
M2Depth: Unifying Monocular Depth Foundation Priors with Multi-View Stereo
Byeonggwon Lee, Sanggi Lee, Siwoo Lee +2
Deep learning-based Multi-View Stereo (MVS) has advanced significantly but often generalizes poorly to unseen scenes, particularly in occluded areas or regions with limited view ov…
cs.CV2026
PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis
Inseong Choi, Siwoo Lee, Seung-Hun Nam +1
Diffusion models are promising for sparse-view novel view synthesis (NVS), as they can generate pseudo-ground-truth views to aid 3D reconstruction pipelines like 3D Gaussian Splatt…
physics.chem-ph2023
Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials
Siwoo Lee, Stefan Heinen, Danish Khan +1
We present an automated data-collection pipeline involving a convolutional neural network and a large language model to extract user-specified tabular data from peer-reviewed liter…