5 papers
SAM2Matting: Generalized Image and Video Matting
Ruiqi Shen, Guangquan Jie, Chang Liu +1
Despite impressive advances in image matting, video matting remains challenging due to the inherent gap between high-level tracking, which requires frame-wise understanding, and lo…
ROSE: Retrieval-Oriented Segmentation Enhancement
Song Tang, Guangquan Jie, Henghui Ding +1
Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inability to incorporate u…
Ref-SAM3D: Bridging SAM3D with Text for Reference 3D Reconstruction
Yun Zhou, Yaoting Wang, Guangquan Jie +2
SAM3D has garnered widespread attention for its strong 3D object reconstruction capabilities. However, a key limitation remains: SAM3D cannot reconstruct specific objects referred…
ReferSplat: Referring Segmentation in 3D Gaussian Splatting
Shuting He, Guangquan Jie, Changshuo Wang +4
We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, whi…
Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
Kaining Ying, Henghui Ding, Guangquan Jie +1
Referring audio-visual segmentation (RAVS) has recently seen significant advancements, yet challenges remain in integrating multimodal information and deeply understanding and reas…