Pedestrian trajectory prediction plays a crucial role in understanding human behavior and intentions. Due to the inherent randomness in human movement, current research constructs trajectories in stochastic space and uses diffusion models to reverse the denoising process. The commonly used denoising model, Transformer, is affected by uneven noise sampling, leading to confusion between temporal consistency and randomness across multiple time points. To address this issue, we propose a novel framework named Stochastic-Aware Mamba Diffusion (SAMD), which combines Stochastic-Aware Mamba with the Diffusion model to predict motion noise and motion states in the stochastic space. It utilizes a temporal aggregator to extract temporal consistency features. We construct a motion-selective state space model, which includes the adaptive transition between consistency motion states and stochastic states for balancing stability and diversity. The motion gating unit activates pertinent information within motion states to extract motion noise for trajectory prediction. Our approach achieves state-of-the-art results on the ETH-UCY and SDD datasets while significantly reducing the computational cost.

Point cloud-based 3-D object detection is a significant and critical issue in numerous applications. While most existing methods attempt to capitalize on the geometric characteristics of point clouds, they neglect the internal semantic properties of point and the consistency between the semantic and geometric clues. We introduce a semantic consistency (SC) mechanism for 3-D object detection in this article, by reasoning about the semantic relations between 3-D object boxes and its internal points. This mechanism is based on a natural principle: the semantic category of a 3-D bounding box should be consistent with the categories of all points within the box. Driven by the SC mechanism, we propose a novel SC network (SCNet) to detect 3-D objects from point clouds. Specifically, the SCNet is composed of a feature extraction module, a detection decision module, and a semantic segmentation module. In inference, the feature extraction and the detection decision modules are used to detect 3-D objects. In training, the semantic segmentation module is jointly trained with the other two modules to produce more robust and applicable model parameters. The performance is greatly boosted through reasoning about the relations between the output 3-D object boxes and segmented points. The proposed SC mechanism is model-agnostic and can be integrated into other base 3-D object detection models. We test the proposed model on three challenging indoor and outdoor benchmark datasets: ScanNetV2, SUN RGB-D, and KITTI. Furthermore, to validate the universality of the SC mechanism, we implement it in three different 3-D object detectors. The experiments show that the performance is impressively improved and the extensive ablation studies also demonstrate the effectiveness of the proposed model.

LiDAR-based point cloud segmentation is a significant and challenging task for 3D scene understanding. Recent voxel-based methods are often built on submanifold sparse residual calculation with small kernel size, which limits the local feature interactions and neglects the global contextual information. In this paper, we propose a local-to-global perception LiDAR-based point cloud segmentation network LGPSeg. From the local perspective, we design the Dynamic Spatial Aggregation Convolution to expand the receptive field range while avoiding a large increase in the model parameters. From the global perspective, we propose the BEV-Voxel Fusion to aggregate the global contextual information on the BEV feature maps through advanced 2D operators. By combining the local and global features, the 3D object and background information can be better captured. Our method achieves state-of-the-art results on two large datasets, SemanticKITTI and nuScenes, and even outperformed multimodal-based methods.

Scene graph generation is a significant and challenging task for scene understanding. Most existing methods are confined to the 2D space (i.e. images) or additional use of segmentation information, while neglecting the richer spatial and geometric information of 3D space. In this paper, we propose a novel method to generate scene graphs from 3D point clouds. Specifically, our model consists of three parts: a point feature extraction backbone, a box head, and a relation head. The feature extraction backbone extracts base features directly from raw point clouds, and the box head produces detected 3D bounding boxes. Final 3D scene graphs are obtained from the relation head which takes the extracted features and 3D boxes as inputs. We also design a point RoI module which sequentially processes points inside 3D boxes with a bidirectional LSTM. To further leverage the geometric characteristics of point clouds, we propose a location attention module which learns the influence of relative locations between objects. We introduce the RelationScanNet dataset with densely annotated semantic and geometric relationships, which extends one of the most widely used dataset ScanNetV2 in 3D indoor scene understanding. We test the proposed method on the RelationScanNet dataset and 3DSSG dataset. The results prove the strength of our method.