PR-IQA: partial-reference image quality assessment for diffusion-based novel view synthesis

Inseong Choi*, Siwoo Lee*, Seung-Hun Nam†, and Soohwan Song† († corresponding authors)

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026 (Accepted)

Efficient TSP-based task group allocation for multi-task multi-agent pickup and delivery

Seungbeen Lee, Chanyoung Lee, Wonpil Yu, and Soohwan Song

IEEE Access, 2025 [PDF]

Online 3d gaussian splatting modeling with novel view selection

Byeonggwon Lee, Junkyu Park , Khang Truong Giang†, and Soohwan Song† († corresponding authors)

International Joint Conference on Artificial Intelligence (IJCAI), 2025 [PDF]

Stereo-GS: online 3d gaussian splatting mapping using stereo depth estimation

Junkyu Park*, Byeonggwon Lee*, Sanggi Lee, and Soohwan Song

Electronics, 2025 [PDF]

MVS-GS: high-quality 3d gaussian splatting mapping via online multi-view stereo

Byeonggwon Lee, Junkyu Park , Khang Truong Giang, Sungho Jo†, and Soohwan Song† († corresponding authors)

IEEE Access, 2025 [PDF]

TopicFM+: boosting accuracy and efficiency of topic-assisted feature matching

Khang Truong Giang, Soohwan Song†, and Sungho Jo† († corresponding authors)

IEEE Transactions on Image Processing, 2024 [PDF]

Learning to produce semi-dense correspondences for visual localization

Khang Truong Giang, Soohwan Song†, and Sungho Jo† († corresponding authors)

Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [PDF] 

[Oral Presentation (Top < 3.3% = 90/2719)]

Anytime lifelong multi-agent pathfinding in topological maps

Soohwan Song, Kiin Na, and Wonpil Yu

IEEE Access, 2023 [PDF] [Video]

TopicFM: robust and interpretable topic-assisted feature matching

Khang Truong Giang, Soohwan Song†, and Sungho Jo† († corresponding authors)

AAAI Conference on Artificial Intelligence (AAAI), 2023 [PDF]

Prior depth-based multi-view stereo network for online 3D model reconstruction

Soohwan Song*, Khang Truong Giang*, Daekyum Kim, and Sungho Jo (* co-first authors)

Pattern Recognition, 2022 [PDF] [Video]

Curvature-guided dynamic scale networks for multi-view stereo

Khang Truong Giang, Soohwan Song, and Sungho Jo

International Conference on Learning Representations (ICLR), 2022 [PDF]

View path planning via online multi-view stereo for 3D modeling of large-scale structures

Soohwan Song, Daekyum Kim, and Sunghee Choi 

IEEE Transactions on Robotics, 2021 [PDF] [Video]

Sequential depth completion with confidence estimation for 3D model reconstruction

Khang Truong Giang*, Soohwan Song*, Daekyum Kim, and Sunghee Choi (* co-first authors)

IEEE Robotics and Automation Letters, 2021 [PDF] [Video]

Online coverage and inspection planning for 3D modeling

Soohwan Song, Daekyum Kim, and Sungho Jo

Autonomous Robots, 2020 [PDF] [Page] [Video]

Active 3D modeling via online multi-view stereo

Soohwan Song, Daekyum Kim, and Sungho Jo

IEEE International Conference on Robotics and Automation (ICRA), 2020 [PDF] [Video1] [Video2]

Surface-based exploration for autonomous 3D modeling 

Soohwan Song and Sungho Jo

IEEE International Conference on Robotics and Automation (ICRA), 2018 [PDF] [Video]

Online inspection path planning for autonomous 3D modeling using a micro-aerial vehicle

Soohwan Song and Sungho Jo

IEEE International Conference on Robotics and Automation (ICRA), 2017 [PDF] [Video] 

3D Reconstruction using a sparse laser scanner and a single camera for outdoor autonomous vehicle

Honggu Lee, Soohwan Song, and Sungho Jo 

IEEE International Conference on Intelligent Transportation Systems (ITSC), 2016 [PDF]

Traversability classification using super-voxel method in unstructured terrain

Soohwan Song and Sungho Jo

Robot Intelligence Technology and Applications, 2015 [PDF]

Boundary-enhanced supervoxel segmentation for sparse outdoor LiDAR data

Soohwan Song, Honggu Lee, and Sungho Jo 

Electronics Letters, 2014 [PDF] [Page] [Video]