지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2023.12
- 수록면
- 966 - 972 (7page)
- DOI
- 10.5302/J.ICROS.2023.23.0143
이용수
초록· 키워드
오류제보하기
Autonomous systems require a profound understanding of their surroundings, encompassing both semantic and 3D geometry. This study focuses on advancing 3D semantic scene completion approaches using a camera. Building upon the foundation laid by VoxFormer [1], which is recognized for its state-of-the-art performance in 3D semantic scene completion, our approach involves two distinct stages. In the initial stage, scene completion is done with depth images, while in the second stage, the final 3D scene completion is performed using masked autoencoder. To enhance the performance of VoxFormer, we introduced two key modifications. First, we modified the first stage using multi-scale feature maps. Second, we further modified the first stage using a masked autoencoder. Experimental results, based on the adapted VoxFormer model in both stages are presented. Our two proposed approaches exhibit notable improvements, particularly in the context of small objects. However, these enhancements warrant further investigation for optimization and refinement.
목차
Abstract
Ⅰ. 서론
Ⅱ. 관련 연구
Ⅲ. VoxFormer 개선 구조
Ⅳ. 실험 결과
Ⅴ. 결론
REFERENCES
참고문헌 (10)
참고문헌 신청
Y. Li, Z. Yu, C. Choy, C. Xiao, J. M. Alvarez, S. Fidler, C. Feng, and A. Anadkumar, “VoxFormer: Sparse voxel transformer for camera-based 3D semantic scene completion," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp
K. He, X. Chen, S. Xie, Y. Li, P. Dollar, and R. Girshick. “Masked autoencoders are scalable vision learners," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000-16009, 2022.
L. Roldao, R. de Charette, and S. Verroust-Blondet, “LMSCNet: Lightweight multiscale 3d semantic completion," International Conference on 3D Vision (3DV), pp. 111-119, 2020.
Z. Xia, Y. Liu, X. Li, X. Zhu, Y. Li, Y. Hou, and Y. Qiao, “SCPNet: Semantic scene completion on point cloud," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17642-17651, 2023.
X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, “Deformable DETR: Deformable transformers for end-to-end object detection," arXiv:2010.04159, 2021.
K. He, X. Chen, S. Xie, Y. Li, P. Dollar, and R. Girshick. “Masked autoencoders are scalable vision learners," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000-16009, 2022.
L. Roldao, R. de Charette, and S. Verroust-Blondet, “LMSCNet: Lightweight multiscale 3d semantic completion," International Conference on 3D Vision (3DV), pp. 111-119, 2020.
Z. Xia, Y. Liu, X. Li, X. Zhu, Y. Li, Y. Hou, and Y. Qiao, “SCPNet: Semantic scene completion on point cloud," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17642-17651, 2023.
X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, “Deformable DETR: Deformable transformers for end-to-end object detection," arXiv:2010.04159, 2021.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Network Completion: Beyond Matrix Completion
한국통신학회 학술대회논문집
2020 .08
-
Real-time Deep Learning-based Scene Recognition Model For Metaverse Applications
한국통신학회 학술대회논문집
2022 .02
-
Structure-Object Hierarchical Reconstruction Framework for Effective Semantic Scene Completion
한국통신학회 학술대회논문집
2025 .02
-
Performance Analysis of Object-based Scene Recognition Algorithm using Mask R-CNN
한국통신학회 학술대회논문집
2021 .06
-
실내 환경에서 멀티-뷰 RGB-D 영상들을 활용하는 3차원 의미적 장면 분할
제어로봇시스템학회 논문지
2023 .03
-
미디어 제작을 위한 씬 검출 기법
한국방송미디어공학회 학술발표대회 논문집
2022 .06
-
서로 다른 3차원 장면으로의 3차원 사람 동작 시퀀스 매핑
대한전자공학회 학술대회
2022 .06
-
Semantic Scene Graph Map 기반의 실내 장면 분류
제어로봇시스템학회 국내학술대회 논문집
2018 .05
-
Depth completion을 위한 딥러닝 모델 비교 분석
한국통신학회 학술대회논문집
2022 .06
-
A New Approach for Scene Recognition using a Deep Convolution Neural Network
대한전자공학회 학술대회
2021 .06
-
Development and Evaluation of Text-to-Scene Model for Korean Language Writing Education as a Foreign Language
한국컴퓨터게임학회논문지
2018 .01
-
Autoencoder-Based binary mask segmentation for Masked Faces
한국통신학회 학술대회논문집
2023 .06
-
A Scene-Specific Object Detection System Utilizing the Advantages of Fixed-Location Cameras
Journal of information and communication convergence engineering
2023 .12
-
3차원 장면 그래프를 이용한 실내 환경 변화 모델링
제어로봇시스템학회 논문지
2019 .08
-
단계별 비용 체적 정규화를 이용한 자기 지도 학습 기반 단안 씬(Scene) 플로우 추정
대한전자공학회 학술대회
2020 .11
-
Masked Autoencoder 를 활용한 소아 폐렴 진단
한국통신학회 인공지능 학술대회 논문집
2023 .09
-
An Improvement of Deep Learning-based Object Detection Scheme for Game Scenes
한국컴퓨터게임학회논문지
2021 .01
-
AI 기반 동적 공간영상 생성 기술 동향
[ETRI] 전자통신동향분석
2025 .04
-
Arbitrary-shaped Scene Text Detection based on Multi-scale Feature Enhancement Network
한국정보과학회 학술발표논문집
2022 .06
-
비디오 요약을 위한 장면분할 및 장면별 스코어링 시스템
대한전자공학회 학술대회
2019 .06
이 논문의 저자 정보
최근 본 자료
댓글(0)
0