Related papers: PointCLM: A Contrastive Learning-based Framework f…

Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. For the last few decades, existing registration algorithms have struggled in situations with large transformations, noise, and time constraints.…

Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering. However, we identify several drawbacks with na\"ively aligning representation distributions. We…

3D point cloud registration ranks among the most fundamental problems in remote sensing, photogrammetry, robotics and geometric computer vision. Due to the limited accuracy of 3D feature matching techniques, outliers may exist, sometimes…

In this paper, we present a novel approach for multiview point cloud registration. Different from previous researches that typically employ a global scheme for multiview registration, we propose to adopt an incremental pipeline to…

We propose a robust method for point cloud registration that can handle both unknown scales and extreme outlier ratios. Our method, dubbed PCR-99, uses a deterministic 3-point sampling approach with two novel mechanisms that significantly…

This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target…

Recent advances in point cloud In-Context Learning (ICL) have demonstrated strong multitask capabilities. Existing approaches typically adopt a Masked Point Modeling (MPM)-based paradigm for point cloud ICL. However, MPM-based methods…

Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the…

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…

Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration. This paper proposes a learning framework COTReg by jointly considering the pointwise and structural matchings to…

We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations. The reason is that objects in…

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…

Point clouds have grown in importance in the way computers perceive the world. From LIDAR sensors in autonomous cars and drones to the time of flight and stereo vision systems in our phones, point clouds are everywhere. Despite their…

Iterative Closest Point (ICP) solves the rigid point cloud registration problem iteratively in two steps: (1) make hard assignments of spatially closest point correspondences, and then (2) find the least-squares rigid transformation. The…

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:…

In recent years, point cloud representation has become one of the research hotspots in the field of computer vision, and has been widely used in many fields, such as autonomous driving, virtual reality, robotics, etc. Although deep learning…

This paper addresses the challenges of complex dependencies and diverse anomaly patterns in cloud service environments by proposing a dependency modeling and anomaly detection method that integrates contrastive learning. The method…

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we…