Related papers: Occlusion-Free Conformal Lensing for Spatiotempora…

Building change detection is essential for monitoring urbanization, disaster assessment, urban planning and frequently updating the maps. 3D structure information from airborne light detection and ranging (LiDAR) is very effective for…

Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as…

Though the success of CLIP-based training recipes in vision-language models, their scalability to more modalities (e.g., 3D, audio, etc.) is limited to large-scale data, which is expensive or even inapplicable for rare modalities. In this…

Traditional computer vision models often necessitate extensive data acquisition, annotation, and validation. These models frequently struggle in real-world applications, resulting in high false positive and negative rates, and exhibit poor…

Understanding and reconstructing occluded objects is a challenging problem, especially in open-world scenarios where categories and contexts are diverse and unpredictable. Traditional methods, however, are typically restricted to closed…

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

We present a new learning-based method for multi-frame depth estimation from a color video, which is a fundamental problem in scene understanding, robot navigation or handheld 3D reconstruction. While recent learning-based methods estimate…

Accurate and temporally consistent modeling of human bodies is essential for a wide range of applications, including character animation, understanding human social behavior and AR/VR interfaces. Capturing human motion accurately from a…

Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation. Previous methods have focused on either temporal contexts or local-to-global architectures that embed fixed-length spatio-temporal…

Semantic image and video segmentation stand among the most important tasks in computer vision nowadays, since they provide a complete and meaningful representation of the environment by means of a dense classification of the pixels in a…

The thesis contributes in several important ways to the research area of 3D object category learning and recognition. To cope with the mentioned limitations, we look at human cognition, in particular at the fact that human beings learn to…

Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as occlusion increases the intra-class variance of…

The performance of autonomous systems heavily relies on their ability to generate a robust representation of the environment. Deep neural networks have greatly improved vision-based perception systems but still fail in challenging…

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame 3D point cloud data, and the temporal information is ignored…

Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate…

The rapid growth of location-based services (LBS) has yielded massive amounts of data on human mobility. Effectively extracting meaningful representations for user-generated check-in sequences is pivotal for facilitating various downstream…

Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limited by inherent constraints of point cloud data, particularly…

To reach human performance on complex tasks, a key ability for artificial systems is to understand physical interactions between objects, and predict future outcomes of a situation. This ability, often referred to as intuitive physics, has…

Vision-language-action (VLA) models show potential for general robotic tasks, but remain challenging in spatiotemporally coherent manipulation, which requires fine-grained representations. Typically, existing methods embed 3D positions into…

LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal…