Visual grounding (VG) tasks involve explicit cross-modal alignment, as semantically corresponding image regions are to be located for the language phrases provided. Existing approaches complete such visual-text reasoning in a single-step manner. Their performance causes high demands on large-scale anchors and over-designed multi-modal fusion modules based on human priors, leading to complicated frameworks that may be difficult to train and overfit to specific scenarios. Even worse, such once-for-all reasoning mechanisms are incapable of refining boxes continuously to enhance query-region matching. In contrast, in this paper, we formulate an iterative reasoning process by denoising diffusion modeling. Specifically, we propose a language-guided diffusion framework for visual grounding, LG-DVG, which trains the model to progressively reason queried object boxes by denoising a set of noisy boxes with the language guide. To achieve this, LG-DVG gradually perturbs query-aligned ground truth boxes to noisy ones and reverses this process step by step, conditional on query semantics. Extensive experiments for our proposed framework on five widely used datasets validate the superior performance of solving visual grounding, a cross-modal alignment task, in a generative way. The source codes are available at \url{https://github.com/iQua/vgbase/tree/DiffusionVG}.

翻译：视觉定位（VG）任务涉及显式的跨模态对齐，即需要根据所提供的语言短语定位语义对应的图像区域。现有方法以单步方式完成这类视觉-文本推理，其性能对大规模锚点和基于人类先验的过度设计的多模态融合模块提出了较高要求，导致框架复杂，可能难以训练且易过拟合于特定场景。更严重的是，这种一次性推理机制无法通过持续优化边界框来增强查询-区域匹配。针对这一问题，本文通过去噪扩散建模提出了一种迭代推理过程。具体而言，我们提出了一个语言引导的扩散框架LG-DVG，用于视觉定位，该框架训练模型在语言引导下通过去噪一组带噪边界框来逐步推理查询对象框。为实现这一目标，LG-DVG逐步将查询对齐的真实边界框扰动为带噪边界框，并基于查询语义条件逐步逆转这一过程。在五个广泛使用的数据集上进行的广泛实验验证了我们的框架以生成式方式解决视觉定位这一跨模态对齐任务的优越性能。源代码可在\url{https://github.com/iQua/vgbase/tree/DiffusionVG}获取。