通过单目几何先验增强边界分割，提升隐蔽物体识别能力
BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors
- 在SAM2编码器中直接融合单目深度信息，提供几何线索
- 仅用5个训练周期即达到顶尖性能，显著减少训练成本
- 适合需要精准边界分割的隐蔽目标检测任务
基于SAM2视觉基础模型，本文提出边界增强深度（BED）-SAM2。将SAM2的Hiera编码器结构改进，直接从RGB图像中编码单目深度信息，从而提供几何线索，增强物体边界的精确划分，并有助于提取伪装物体的形状。BED-SAM2在多个显著与伪装物体检测任务中表现出媲美前沿的性能，且仅需五个训练周期即可达成优异效果。
原文摘要 · Abstract (English)
Building upon the SAM2 vision foundation model for downstream segmentation, this study introduces Boundary Enhanced Depth (BED)-SAM2. The SAM2 Hiera encoder architecture is modified to directly encode monocular depth information from RGB images, thereby providing geometric cues that enhance object boundary delineation and facilitate the extraction of camouflaged object shapes. BED-SAM2 demonstrates competitive state-of-the-art performance across multiple salient and camouflaged object detection tasks with as few as five training epochs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。