The 10th International Conference on Next Generation Computing 2024 (2024.11)바로가기
페이지
pp.345-348
저자
Kang-San Kim, Jae-Hyeok Kang, Yeong-Ju Lee, Youngbae Hwang
언어
영어(ENG)
URL
https://www.earticle.net/Article/A468881
원문정보
초록
영어
This paper presents a method to optimize 3D Gaussian Splatting, improving computational efficiency for real-time applications on edge devices like Jetson AGX Xavier. By applying pruning and quantization techniques, we enhance computing speed with minimal degradation on image quality. Our method enables efficient 3D scene reconstruction on resource-limited devices, making it suitable for AR/VR and autonomous driving.
목차
Abstract I. INTRODUCTION II. RELATED WORK A. 3D Reconstruction B. Network Pruning and Quantizaiton III. METHOD A. Overview B. Gaussian Clustering with HDBSCAN C. Gaussian Pruning IV. EXPERIMENTS A. Experimental Settings B. Evaluation of Pruning Ratio C. Performance Comparison on Edge Device D. Ablation Study V. CONCLUSION ACKNOWLEDGMENT REFERENCES
키워드
3D reconstructionGaussian SplattingNetwork compressionEdge Device
저자
Kang-San Kim [ Department of Intelligent Systems and Robotics Chungbuk National University Cheongju, Republic of Korea ]
Jae-Hyeok Kang [ Department of Intelligent Systems and Robotics Chungbuk National University Cheongju, Republic of Korea ]
Yeong-Ju Lee [ Department of Intelligent Systems and Robotics Chungbuk National University Cheongju, Republic of Korea ]
Youngbae Hwang [ Department of Intelligent Systems and Robotics Chungbuk National University Cheongju, Republic of Korea ]
Corresponding Author