用输入级融合提升立体匹配，让编码器自己学跨视图对应关系。
BINO: Encoder Centric Self Supervised Stereo With Native Pair Input
- 输入阶段融合左右图像生成微单元标记，增强立体结构学习。
- 仅在KITTI物体上预训练，仍优于所有基线模型的冻结特征性能。
- 轻量编码器实现接近CroCo-v2效果，适合资源受限场景使用。
立体视觉需要保留精细的跨视图对应关系，而不仅是语义相似性。近期自监督视觉模型迁移效果好，但并非为此目标设计，几何导向方法常依赖双目解码器或显式连接模块进行预训练。BINO提出：是否能在紧凑编码器内部学习强双目结构？通过在输入阶段融合校正后的图像对，生成立体微单元标记，并采用行感知的补丁相位位置编码。训练使用单视图掩码标记蒸馏，结合遮挡与视图特定外观不一致损失。在仅用KITTI物体数据预训练的严格低资源设置下，BINO在无连接探测器条件下，于代理密集立体、硬负样本检索和KITTI Stereo 2012视差任务中均取得最佳冻结特征表现。使用相同轻量级立体头时，其性能接近CroCo-v2，但所用编码器显著更小。在KITTI Stereo 2015上的补充迁移实验也呈现相同定性趋势。结果表明，大量原本归于独立连接模块的跨视图推理能力，可内化至紧凑且可复用的编码器中。
原文摘要 · Abstract (English)
Stereo needs features that preserve fine cross view correspondence rather than only semantic similarity. Recent self supervised vision models transfer well, but they are not built for this goal, and geometry focused methods often rely on a binocular decoder or another explicit linkage module during pretraining. BINO asks whether strong binocular structure can instead be learned inside a compact encoder. It does this by fusing the rectified pair at the input stage, forming stereo micro cell tokens, and using a row aware patch phase positional encoding. Training uses one view masked token only distillation together with occlusion and view specific appearance mismatch. In a strict low resource setting with pretraining only on KITTI object, BINO gives the best frozen descriptor results under a no linkage probe among all compared baselines on proxy dense stereo, hard negative retrieval, and KITTI Stereo~2012 disparity. With the same lightweight stereo head for every encoder, it stays near CroCo~v2 while using a much smaller encoder. Supplementary transfer experiments on KITTI Stereo~2015 show the same qualitative trend. These results suggest that much of the cross view reasoning often assigned to a separate linkage module can be learned inside a compact and reusable encoder.
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。