Related papers: SCoDA: Domain Adaptive Shape Completion for Real S…

Conventional methods for point cloud completion, typically trained on synthetic datasets, face significant challenges when applied to out-of-distribution real-world scans. In this paper, we propose an effective yet simple source-free domain…

Deep learning approaches achieve prominent success in 3D semantic segmentation. However, collecting densely annotated real-world 3D datasets is extremely time-consuming and expensive. Training models on synthetic data and generalizing on…

Source-Free Domain Adaptation (SFDA) addresses the challenge of adapting a model to a target domain without access to the data of the source domain. Prevailing methods typically start with a source model pre-trained with full supervision…

3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect…

Domain Adaptation (DA) approaches achieved significant improvements in a wide range of machine learning and computer vision tasks (i.e., classification, detection, and segmentation). However, as far as we are aware, there are few methods…

Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to…

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact…

LiDAR-based 3D object detection is an indispensable task in advanced autonomous driving systems. Though impressive detection results have been achieved by superior 3D detectors, they suffer from significant performance degeneration when…

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete…

Domain shift presents a significant challenge in applying Deep Learning to the segmentation of 3D medical images from sources like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). Although numerous Domain Adaptation methods…

Solving the domain shift problem during inference is essential in medical imaging, as most deep-learning based solutions suffer from it. In practice, domain shifts are tackled by performing Unsupervised Domain Adaptation (UDA), where a…

As 3D scanning solutions become increasingly popular, several deep learning setups have been developed geared towards that task of scan completion, i.e., plausibly filling in regions there were missed in the raw scans. These methods,…

Point completion refers to complete the missing geometries of objects from partial point clouds. Existing works usually estimate the missing shape by decoding a latent feature encoded from the input points. However, real-world objects are…

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data…

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…

How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, and then refine its local details. We are motivated to…

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real…

Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including…

Due to its robust and precise distance measurements, LiDAR plays an important role in scene understanding for autonomous driving. Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations, which are…