Related papers: LCD: Learned Cross-Domain Descriptors for 2D-3D Ma…

Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…

Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart. However, it is seldom used in visual pose estimation due to the difficulty in obtaining 2D-3D image to point cloud correspondences. In this…

The recent development of high-precision subsea optical scanners allows for 3D keypoint detectors and feature descriptors to be leveraged on point cloud scans from subsea environments. However, the literature lacks a comprehensive survey to…

Domain adaptation is critical for success when confronting with the lack of annotations in a new domain. As the huge time consumption of labeling process on 3D point cloud, domain adaptation for 3D semantic segmentation is of great…

High-quality 3D reconstructions from endoscopy video play an important role in many clinical applications, including surgical navigation where they enable direct video-CT registration. While many methods exist for general multi-view 3D…

Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD…

We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment. Point cloud patches are extracted, canonicalised with…

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the…

For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. However, this may still incur a large domain gap due to the lack…

While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However,…

In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this…

Achieving monocular camera localization within pre-built LiDAR maps can bypass the simultaneous mapping process of visual SLAM systems, potentially reducing the computational overhead of autonomous localization. To this end, one of the key…

We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between…

3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…

Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…

With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport…

LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…

Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other…