Related papers: Instance by Instance: An Iterative Framework for M…

We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise alignment and the globally consistent refinement. The…

We tackle the problem of learning an implicit scene representation for 3D instance segmentation from a sequence of posed RGB images. Towards this, we introduce 3DIML, a novel framework that efficiently learns a neural label field which can…

Monocular 3D detection relies on just a single camera and is therefore easy to deploy. Yet, achieving reliable 3D understanding from monocular images requires substantial annotation, and 3D labels are especially costly. To maximize…

Deformable image registration is inherently a multi-objective optimization (MOO) problem, requiring a delicate balance between image similarity and deformation regularity. These conflicting objectives often lead to poor optimization…

Deformable registration consists of finding the best dense correspondence between two different images. Many algorithms have been published, but the clinical application was made difficult by the high calculation time needed to solve the…

Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation, and 2) the complexity of two-stage approaches. To resolve…

Multi-instance learning attempts to learn from a training set consisting of labeled bags each containing many unlabeled instances. Previous studies typically treat the instances in the bags as independently and identically distributed.…

We investigate a variation of the 3D registration problem, named multi-model 3D registration. In the multi-model registration problem, we are given two point clouds picturing a set of objects at different poses (and possibly including…

We describe a convex programming framework for pose estimation in 2D/3D point-set registration with unknown point correspondences. We give two mixed-integer nonlinear program (MINP) formulations of the 2D/3D registration problem when there…

Instance detection (InsDet) is a long-lasting problem in robotics and computer vision, aiming to detect object instances (predefined by some visual examples) in a cluttered scene. Despite its practical significance, its advancement is…

Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of different datasets make these methods become particularly…

We propose to tackle the problem of multiview 2D/3D rigid registration for intervention via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$). $\text{POINT}^2$ learns to establish 2D point-to-point…

Re-identification (ReID) is to identify the same instance across different cameras. Existing ReID methods mostly utilize alignment-based or attention-based strategies to generate effective feature representations. However, most of these…

This paper presents one of the first learning-based NeRF 3D instance segmentation pipelines, dubbed as Instance Neural Radiance Field, or Instance NeRF. Taking a NeRF pretrained from multi-view RGB images as input, Instance NeRF can learn…

Spatial registration across different visual modalities is a critical but formidable step in multi-modality image fusion for real-world perception. Although several methods are proposed to address this issue, the existing registration-based…

Point cloud registration aligns multiple unposed point clouds into a common reference frame and is a core step for 3D reconstruction and robot localization without initial guess. In this work, we cast registration as conditional generation:…

3D instance segmentation plays a crucial role in comprehending 3D scenes. Despite recent advancements in this field, existing approaches exhibit certain limitations. These methods often rely on fixed instance positions obtained from sampled…

Monocular 3D object detection has recently shown promising results, however there remain challenging problems. One of those is the lack of invariance to different camera intrinsic parameters, which can be observed across different 3D object…

This paper introduces key machine learning operations that allow the realization of robust, joint 6D pose estimation of multiple instances of objects either densely packed or in unstructured piles from RGB-D data. The first objective is to…

Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth…