Sung Soo Hwang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Sung Soo Hwang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Seong Dae Kim
Department of Electrical Engineering, KAIST, Daejeon, Republic of Korea
5 shared publications - Il Yong Chun
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Republic of Korea
4 shared publications - Sang Jun Lee
School of Computer Science and Engineering, Handong Global University, Pohang-si, Korea
4 shared publications Hee-Dong Kim
2 shared publications- Hye Bin Yoo
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Republic of Korea
2 shared publications - Hyun Min Han
Department of Information and Communication Engineering, Handong Global University, Pohang, Republic of Korea
2 shared publications
Latest Publications
- 15 August 2026
- Published by Elsevier in Measurement
- Vol. 290
Length estimation of tilted object using ground point detection in single view
- 15 August 2026
- Published by Elsevier in Measurement
- Vol. 290
Length estimation of tilted object using ground point detection in single view
- 31 March 2026
- Published by Institute of Control, Robotics and Systems in Journal of Institute of Control, Robotics and Systems
- Vol. 32 (3) , 411-420
In-stargazer: Helmet-mounted Camera System for Localization in Large-scale Industrial Environments
- 31 March 2026
- Published by Institute of Control, Robotics and Systems in Journal of Institute of Control, Robotics and Systems
- Vol. 32 (3) , 411-420
In-stargazer: Helmet-mounted Camera System for Localization in Large-scale Industrial Environments
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
VOCA: A VLM-Optimized Call Approach for Zero-Shot Navigation Using Target-Context Cues
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Open AccessVOCA: A VLM-Optimized Call Approach for Zero-Shot Navigation Using Target-Context Cues
- Open Access
- 1 December 2025
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 31 (5) , 9-16
Gaussian Splitting Photography Strategy for Light Reflection and Repetition Structure in Corridors
- 1 December 2025
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 31 (5) , 9-16
Open AccessGaussian Splitting Photography Strategy for Light Reflection and Repetition Structure in Corridors
- 19 September 2024
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 26 (2) , 301-313
Embedding Object Avoidance to End-To-End Driving Systems by Input Data Manipulation
- 19 September 2024
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 26 (2) , 301-313
Embedding Object Avoidance to End-To-End Driving Systems by Input Data Manipulation
- Open Access
- 22 July 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (4) , 1-22
Improving Neural Radiance Fields Using Near-Surface Sampling with Point Cloud Generation
Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and performs sampling only near the estimated surface. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF methods. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.
- 22 July 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (4) , 1-22
Open AccessImproving Neural Radiance Fields Using Near-Surface Sampling with Point Cloud Generation
Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and performs sampling only near the estimated surface. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF methods. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.
- Open Access
Improving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generation
Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and sampling is performed around there only. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.
Open AccessImproving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generation
Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and sampling is performed around there only. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.
- 4 November 2023
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 24 (6) , 1577-1587
Survey of Technology in Autonomous Valet Parking System
- 4 November 2023
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 24 (6) , 1577-1587
Survey of Technology in Autonomous Valet Parking System
- 20 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (3) , 2800-2813
Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.
- 20 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (3) , 2800-2813
Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.
- Open Access
Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.
Open AccessImproved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.