模仿人脑分层处理，用多阶段线索融合提升单目深度估计精度
THIRDEYE: Cue-Aware Monocular Depth Estimation via Brain-Inspired Multi-Stage Fusion
- 分三阶段模拟视觉皮层，逐级融合遮挡、明暗、透视等视觉线索
- 通过可学习权重机制动态评估各线索可靠性，生成高分辨率深度图
- 依赖预训练冻结模块，只需少量微调即可达到优异性能
单目深度估计传统方法直接从RGB像素中学习深度，忽略了人类视觉系统依赖的显式单目线索（如遮挡边界、明暗变化、透视）。本文提出ThirdEye，一种基于脑启发的多阶段线索融合框架：通过预训练且冻结的专用网络主动提供各类线索，并在模拟视觉皮层层级（V1→V2→V3）中逐步融合。该过程引入基于键值的工作记忆模块，按线索可靠性加权融合。最终由自适应分桶注意力头生成高分辨率视差图。由于线索专家网络固定，ThirdEye继承大量外部监督信号，仅需少量微调即可取得良好表现。本版本补充了架构细节、神经科学依据及更完整的实验设置，定量结果将在后续修订中呈现。
原文摘要 · Abstract (English)
Monocular depth estimation methods traditionally train deep models to infer depth directly from RGB pixels. This implicit learning often overlooks explicit monocular cues that the human visual system relies on, such as occlusion boundaries, shading, and perspective. Rather than expecting a network to discover these cues unaided, we present ThirdEye, a cue-aware pipeline that deliberately supplies each cue through specialised, pre-trained, and frozen networks. These cues are fused in a three-stage cortical hierarchy (V1->V2->V3) equipped with a key-value working-memory module that weights them by reliability. An adaptive-bins transformer head then produces a high-resolution disparity map. Because the cue experts are frozen, ThirdEye inherits large amounts of external supervision while requiring only modest fine-tuning. This extended version provides additional architectural detail, neuroscientific motivation, and an expanded experimental protocol; quantitative results will appear in a future revision.
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。