We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introduce auxiliary gradient supervision to enhance focus on regions with finer details. Furthermore, we outline practical training strategies tailored for DIS to improve map quality and training process. To validate the general applicability of our approach, we conduct extensive experiments on four tasks to evince that BiRefNet exhibits remarkable performance, outperforming task-specific cutting-edge methods across all benchmarks. Our codes are available at https://github.com/ZhengPeng7/BiRefNet.

翻译：本文提出了一种新颖的双边参考框架（BiRefNet），用于高分辨率二分图像分割（DIS）。该框架包含两个核心组件：定位模块（LM）和基于我们提出的双边参考（BiRef）的重建模块（RM）。定位模块利用全局语义信息辅助目标定位。在重建模块中，我们采用BiRef进行重建过程，其中图像的分层块提供源参考，而梯度图则作为目标参考。这些组件协同工作以生成最终的预测图。我们还引入了辅助梯度监督，以增强对精细细节区域的关注。此外，我们针对DIS任务设计了实用的训练策略，以提升预测图质量和训练过程。为了验证我们方法的普适性，我们在四个任务上进行了广泛的实验，结果表明BiRefNet表现出卓越的性能，在所有基准测试中均超越了特定任务的先进方法。我们的代码可在 https://github.com/ZhengPeng7/BiRefNet 获取。