6 papers
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…
Online 3D Gaussian Splatting Modeling with Novel View Selection
Byeonggwon Lee, Junkyu Park, Khang Truong Giang +1
This study addresses the challenge of generating online 3D Gaussian Splatting (3DGS) models from RGB-only frames. Previous studies have employed dense SLAM techniques to estimate 3…
MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo
Byeonggwon Lee, Junkyu Park, Khang Truong Giang +2
This study addresses the challenge of online 3D model generation for neural rendering using an RGB image stream. Previous research has tackled this issue by incorporating Neural Ra…
Conditional Latent ODEs for Motion Prediction in Autonomous Driving
Khang Truong Giang, Yongjae Kim, Andrea Finazzi
This paper addresses imitation learning for motion prediction problem in autonomous driving, especially in multi-agent setting. Different from previous methods based on GAN, we pre…
Learning to Produce Semi-dense Correspondences for Visual Localization
Khang Truong Giang, Soohwan Song, Sungho Jo
This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior s…
TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matching
Khang Truong Giang, Soohwan Song, Sungho Jo
This study tackles the challenge of image matching in difficult scenarios, such as scenes with significant variations or limited texture, with a strong emphasis on computational ef…