Semi-supervised underwater object detection aims to obtain high-quality pseudo-labeled samples from an amount of unlabeled data, addressing the issue of missing data labels in underwater environments. In this work, we propose a grid marker-assisted image enhancement framework for semi-supervised underwater target detection (SSUTD-GMAIE). By analyzing the color distribution of unlabeled images in the color space grid, we guide balanced image enhancement to achieve semi-supervised underwater object detection. Specifically, we construct a 3D network based on the image color space, dividing the color space into several sub-regions. Each cubic region in the grid represents a certain range of color subspaces. Subsequently, we calculate the mean color values of all unlabeled images and statistically determine the probability of each cubic sample appearing in the grid. Meanwhile, we introduce a grid marker-assisted underwater image enhancement method. This method enhances training images based on network labeling information, sampling color information using random probabilities and sample distribution states, ensuring the authenticity of the enhanced images while reducing the color distribution difference between the enhanced images and the unlabeled images. This enhancement method is applied to the teacher-student model, achieving state-of-the-art performance on two semi-supervised underwater object detection benchmark datasets, demonstrating the effectiveness and superiority of our framework.