DepthFocus：面向透视场景的可控深度估计
DepthFocus: Controllable Depth Estimation for See-Through Scenes
把立体深度估计从静态前馈改为以物理参考深度为条件的可控计算，用双条件机制动态调制特征，可直接借鉴到透明/反射场景的多层深度恢复与意图驱动感知。
原文依据 redefines stereo depth estimation as condition-aware control
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现实世界中的深度很少是单一的。透射材料会造成分层歧义，从而干扰常规感知系统。现有模型仍是被动的；常规方法通常估计锚定在最近表面的静态深度图，即便是近期的多头扩展方法，也因固定的特征表示而受制于表征瓶颈。这与人类视觉形成鲜明对比：人类视觉会主动转移焦点以感知期望的深度。我们提出 DepthFocus，一种可操控的 Vision Transformer，将立体深度估计重新定义为条件感知的控制。我们的模型不提取固定特征，而是基于物理参考深度动态调制其计算，并集成双重条件机制，以选择性地感知与期望焦点对齐的几何结构。借助新构建的大规模合成数据集，DepthFocus 在所有评测基准上均取得最优结果，涵盖标准的单层场景与复杂的多层场景。在不透明区域保持高精度的同时，我们的方法通过在目标距离处选择性地重建几何结构，有效解决了透明与反射场景中的深度歧义。这一能力实现了稳健的、由意图驱动的感知，显著优于现有多层方法，标志着向主动三维感知迈出的重要一步。
英文原文摘要 1516 字符
Depth in the real world is rarely singular. Transmissive materials create layered ambiguities that confound conventional perception systems. Existing models remain passive; conventional approaches typically estimate static depth maps anchored to the nearest surface, and even recent multi-head extensions suffer from a representational bottleneck due to fixed feature representations. This stands in contrast to human vision, which actively shifts focus to perceive a desired depth. We introduce DepthFocus, a steerable Vision Transformer that redefines stereo depth estimation as condition-aware control. Instead of extracting fixed features, our model dynamically modulates its computation based on a physical reference depth, integrating dual conditional mechanisms to selectively perceive geometry aligned with the desired focus. Leveraging a newly curated large-scale synthetic dataset, DepthFocus achieves state-of-the-art results across all evaluated benchmarks, including both standard single-layer and complex multi-layered scenarios. While maintaining high precision in opaque regions, our approach effectively resolves depth ambiguities in transparent and reflective scenes by selectively reconstructing geometry at a target distance. This capability enables robust, intent-driven perception that significantly outperforms existing multi-layer methods, marking a substantial step toward active 3D perception. \noindent Project page: \href https://junhong-3dv.github.io/depthfocus-project/ this https URL .