Related papers: COG: Confidence-aware Optimal Geometric Correspond…

Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and…

Unseen object pose estimation methods often rely on CAD models or multiple reference views, making the onboarding stage costly. To simplify reference acquisition, we aim to estimate the unseen object's pose through a single unposed RGB-D…

The interest in matching non-rigidly deformed shapes represented as raw point clouds is rising due to the proliferation of low-cost 3D sensors. Yet, the task is challenging since point clouds are irregular and there is a lack of intrinsic…

Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose (e.g. the 3D rotation and translation) in a cluttered environment from a single RGB image is a challenging problem. While end-to-end methods have recently demonstrated…

On-board estimation of the pose of an uncooperative target spacecraft is an essential task for future on-orbit servicing and close-proximity formation flying missions. However, two issues hinder reliable on-board monocular vision based pose…

Object pose distribution estimation is crucial in robotics for better path planning and handling of symmetric objects. Recent distribution estimation approaches employ contrastive learning-based approaches by maximizing the likelihood of a…

Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. A key step toward developing trustworthy COD systems is the…

Estimating the 6D pose of objects using only RGB images remains challenging because of problems such as occlusion and symmetries. It is also difficult to construct 3D models with precise texture without expert knowledge or specialized…

The two-stage object pose estimation paradigm first detects semantic keypoints on the image and then estimates the 6D pose by minimizing reprojection errors. Despite performing well on standard benchmarks, existing techniques offer no…

Geometric feature extraction is a crucial component of point cloud registration pipelines. Recent work has demonstrated how supervised learning can be leveraged to learn better and more compact 3D features. However, those approaches'…

For many robotic manipulation and contact tasks, it is crucial to accurately estimate uncertain object poses, for which certain geometry and sensor information are fused in some optimal fashion. Previous results for this problem primarily…

In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to establish dense 2D-3D correspondences. However, current…

Existing camouflaged object detection (COD) methods rely heavily on large-scale datasets with pixel-wise annotations. However, due to the ambiguous boundary, annotating camouflage objects pixel-wisely is very time-consuming and…

3D pose estimation from sparse multi-views is a critical task for numerous applications, including action recognition, sports analysis, and human-robot interaction. Optimization-based methods typically follow a two-stage pipeline, first…

In this paper, we investigate visual-based camera re-localization with neural networks for robotics and autonomous vehicles applications. Our solution is a CNN-based algorithm which predicts camera pose (3D translation and 3D rotation)…

We present a new generalizable NeRF method that is able to directly generalize to new unseen scenarios and perform novel view synthesis with as few as two source views. The key to our approach lies in the explicitly modeled correspondence…

Correspondence identification (CoID) is an essential capability in multi-robot collaborative perception, which enables a group of robots to consistently refer to the same objects within their respective fields of view. In real-world…

Intrinsic image decomposition aims to estimate physically based rendering (PBR) parameters such as albedo, roughness, and metallicity from images. While recent methods achieve strong single-view predictions, applying them independently to…

Extracting point correspondences from two or more views of a scene is a fundamental computer vision problem with particular importance for relative camera pose estimation and structure-from-motion. Existing local feature matching…

With the success of deep learning based approaches in tackling challenging problems in computer vision, a wide range of deep architectures have recently been proposed for the task of visual odometry (VO) estimation. Most of these proposed…