- 게시일자
- 조회수
- 311
박진선 교수 연구실 (VIPLab), AI 분야 최우수 국제학술대회 AAAI 2026 논문 1편 발표
부산대학교 시각지능및인지연구실(VIPLab)이 2026년 1월 20일~27일 싱가포르에서 개최된 AI 분야 최우수 국제학술대회 The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)에 1편의 논문(Main Technical Track)을 발표하였다.
시각지능및인지연구실(VIPLab) 권민성 前 연구원 (현재 Univ. of Minnesota 석사과정, 제1저자), 지도교수 박진선 (좌측부터)
제목: OceanSplat: x-object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction
저자: 권민성, 박진선
연구요약: We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by rendering from horizontally and vertically translated virtual viewpoints, enforcing view consistency to facilitate spatial optimization of 3D Gaussians. Furthermore, we derive synthetic epipolar depth priors from the virtual viewpoints, which serve as self-supervised depth regularizers to compensate for the limited geometric cues in degraded underwater scenes. We also propose a depth-aware alpha adjustment that modulates the opacity of 3D Gaussians during early training based on their depth along the viewing direction, deterring the formation of medium-induced primitives. Our approach promotes the disentanglement of 3D Gaussians from the scattering medium through effective geometric constraints, enabling accurate representation of scene structure and significantly reducing floating artifacts. Experiments on real-world underwater and simulated scenes demonstrate that OceanSplat substantially outperforms existing methods for both scene reconstruction and restoration in scattering media.
Project Page: https://oceansplat.github.io/
주요그림:
- 첨부파일
- 첨부파일이(가) 없습니다.