TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

arXiv:2403.19589v1 Announce Type: new
Abstract: 3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, particularly in indoor settings. However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the \textbf{domain gap} between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the \textbf{lack of data} with …

arxiv captioning cs.cv type