3D scene graph generation is a pivotal task in scene understanding. Its performance is easy to be constrained by the limited availability of annotated data. Currently, the existing solutions on point cloud pre-training usually emphasize on object-centric representations while neglecting the predicate feature learning. This limitation significantly hinders their relational reasoning capabilities, as inter-object relationships are fundamentally governed by predicate features. To enhance 3D Scene Graphs Pre-training, this paper proposes a task-specific Multi-view Invariance Learning framework with Collaborative Cross-modal Regularization. In detail, the inherent horizontal-rotation invariance of 3D objects and their semantic relationships are leveraged to construct a self-supervised paradigm for triplet feature learning. Moreover, our framework harnesses the cross-modal prior knowledge from the vision-language model to regularize model optimization. It could further achieve the semantic discrimination via unsupervised deep clustering. To resolve the knowledge discrepancies arising from the pre-trained model in fine-tuning, a predicate adapter equipped with knowledge filtering gate is devised to selectively aggregate the predicate features of pre-trained model. Extensive experiments demonstrate that our framework is effective in boosting 3D scene graph generation performance, surpassing state-of-the-art ones.

The networks are required to be capable of learning low-level features well when applied to remote sensing image semantic segmentation task. To capture accurate and abundant low-level semantic information, the early feature extractor layer is crucial to the whole network, because all the subsequent features are inferred from that base. To address the low-level feature extraction issue and overcome the shortcomings of traditional convolution like too many parameters or limited receptive field, some novel convolution units have been proposed in the literature. In this paper, we propose two elaborately designed and portable yet effective convolution units, i.e., directional convolution (DC) and large field convolution (LFC), combined as the extractor of low-level semantic features. DC is designed to extract directional features from specific directions, and LFC can achieve a large receptive field with few parameters. Experiment results on two public datasets provide evidence that our convolution units can help deep learning networks improve performance stably and comprehensively compared to the baseline networks.