The problem of change detection in bitemporal synthetic aperture radar (SAR) images is studied. Motivated by utilizing nondense neighborhoods around pixels to detect the change level, a pointwise change detection approach is developed by employing a bilaterally weighted graph model and an irregular Markov random field (I-MRF). First, keypoints with local maximum intensity are extracted from one of the bitemporal images to describe the textural information of the images. Then, two bilaterally weighted graphs with the same topology are constructed for the bitemporal images using the keypoints, respectively. They utilize both the spatial structural and intensity information to provide good performance for feature-based change detection. Next, a change measure function is designed to evaluate the similarity between the graphs, and then the nondense difference image (NDI) is generated. Finally, an I-MRF with a generalized neighborhood system is proposed to classify the discrete keypoints on the NDI. Experiments on real SAR images show that the proposed NDI improves separability between changed and unchanged areas, and I-MRF provides high accuracy and strong noise immunity for change detection tasks with noise-contaminated SAR images. On the whole, the proposed approach is a good candidate for SAR image change detection.