发表机构
School of Computer Science and Engineering, Sun Yat-sen University; Shenzhen Loop Area Institute; Guangdong Key Laboratory of Big Data Analysis and Processing; Baidu Inc.; LightSpeed Studios, Tencent America; School of Computer Science and Artificial Intelligence, Lanzhou University of Technology（中山大学计算机科学与工程学院; 深圳河套学院; 广东省大数据分析与处理重点实验室; 百度公司; 美国光速工作室，腾讯; 兰州理工大学计算机科学与人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究单目深度估计问题，提出ARDepth方法，将其作为结构化自回归生成任务，通过尺度渐进条件和语义感知引导，逐步构建深度表示，实现跨尺度结构一致的深度预测，验证了自回归生成是几何建模的有前景范式。
AI 中文摘要
扩散模型近来成为单目深度估计的主导范式。但它隐含假设深度可通过迭代去噪恢复为全局平滑场，未明确反映场景几何的分段和尺度相关组织。实际上，几何结构在空间尺度上逐步出现。受此启发，我们引入ARDepth，将深度估计表述为结构化自回归生成。它随空间分辨率增加逐步构建深度表示，引入尺度渐进条件注入多尺度视觉特征，语义感知引导提供场景级语义先验。实验结果表明该方法性能强且跨尺度产生结构一致的深度预测。
英文摘要
Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry. In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are constructed in a hierarchical manner. Motivated by this observation, we introduce ARDepth, which formulates depth estimation as structured auto-regressive generation. Instead of recovering depth through global refinement, ARDepth progressively constructs depth representations as spatial resolution increases. To support this generative process, we introduce Scale-Progressive Conditioning (SPC) to inject multi-scale visual features at each generation stage, and Semantic-Aware Guidance (SAG) to provide scene-level semantic priors that enhance global structural consistency. Together, these designs enable the model to capture fine-grained local details while maintaining coherent global geometry. Empirical results demonstrate that our approach achieves strong performance and produces structurally consistent depth predictions across scales, validating auto-regressive generation as a promising alternative paradigm for geometric modeling.
CommentsUnder review
