2 papers
cs.CV2025
SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes
Yuji Wang, Haoran Xu, Yong Liu +2
Reference Audio-Visual Segmentation (Ref-AVS) aims to provide a pixel-wise scene understanding in Language-aided Audio-Visual Scenes (LAVS). This task requires the model to continu…
cs.CV2024
GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting
Jiaze Li, Zhengyu Wen, Luo Zhang +4
The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasteriza…