Siamese AKPConvX for 3-D Point Cloud Change Detection
Abstract
3-D point cloud (PC) change detection is an essential task in urban monitoring. Recent raw-point frameworks preserve native 3-D geometric information more effectively than projection-based or voxelization-based pipelines. However, robust change detection in bitemporal urban scenes remains challenging because irregular sampling, density variation, and temporal misalignment can weaken cross-temporal feature correspondence. To address this problem, we propose adaptive kernel point convolution X (AKPConvX), a point convolution operator that dynamically constructs geometry-conditioned kernels from a learnable weight bank and incorporates a dual adaptive mechanism to jointly model spatial structure and semantic context. AKPConvX replaces rigid-kernel-point parameterization with dynamic depthwise kernel assembly, allowing convolution weights to adapt to local point distributions during inference. Based on this operator, we develop a Siamese encoder–decoder network with inverted bottleneck blocks for effective multiscale feature extraction. We further introduce a position-adaptive difference (PAD) fusion module that reweights reference features according to spatial alignment confidence, thereby reducing false detections caused by temporal misregistration. Experiments are conducted on the two point-level subdatasets of Urb3DCD-V2 defined by the Siamese KPConv benchmark: Urb3DCD-V2-1, corresponding to low-density LiDAR acquisitions, and Urb3DCD-V2-2, corresponding to the multisensor (MS) configuration. On Urb3DCD-V2-1, the proposed method achieves a mean intersection over union for change classes (<inline-formula> <tex-math notation="LaTeX">$mIoU_{ch}$ </tex-math></inline-formula>) of 80.24% and an overall accuracy of 96.26%, outperforming the Siamese KPConv baseline by 5.31% and 2.43%, respectively. On Urb3DCD-V2-2, AKPConvX also consistently improves over Siamese KPConv across <inline-formula> <tex-math notation="LaTeX">$mIoU_{ch}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$mIoU$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$mAcc$ </tex-math></inline-formula>, and <inline-formula> <tex-math notation="LaTeX">$Acc$ </tex-math></inline-formula>.