用自回归模型做单目深度估计，训练数据少且效果好。
Visual Autoregressive Modelling for Monocular Depth Estimation
- 基于视觉自回归先验，分十步逐步生成深度图。
- 仅需7.4万合成样本微调，室内基准达当前最优。
- 适合数据少或需快速适配3D任务的场景。
我们提出一种基于视觉自回归（VAR）先验的单目深度估计方法，作为扩散模型的替代方案。该方法复用大规模文本到图像的VAR模型，并引入分尺度条件上采样机制与无分类器引导。推理过程固定为十步自回归阶段，微调仅需74,000个合成样本，表现优异。在受限训练条件下，室内基准达到最先进水平；应用于室外数据集也表现强劲。本工作确立自回归先验作为几何感知生成模型的新范式，展现出数据可扩展性强、易于适配三维视觉任务的优势。代码已公开于 https://github.com/AmirMaEl/VAR-Depth。
原文摘要 · Abstract (English)
We propose a monocular depth estimation method based on visual autoregressive (VAR) priors, offering an alternative to diffusion-based approaches. Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism with classifier-free guidance. Our approach performs inference in ten fixed autoregressive stages, requiring only 74K synthetic samples for fine-tuning, and achieves competitive results. We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets. This work establishes autoregressive priors as a complementary family of geometry-aware generative models for depth estimation, highlighting advantages in data scalability, and adaptability to 3D vision tasks. Code available at "https://github.com/AmirMaEl/VAR-Depth".
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。