Related papers: PatchContrast: Self-Supervised Pre-training for 3D…

Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints…

Autonomous systems rely on accurate 3D object detection from LiDAR data, yet most detectors are limited to a predefined set of known classes, making them vulnerable to unexpected out-of-distribution (OOD) objects. In this work, we present…

Unsupervised 3D representation learning reduces the burden of labeling multimodal 3D data for fusion perception tasks. Among different pre-training paradigms, differentiable-rendering-based methods have shown most promise. However, existing…

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike all existing methods which usually require a large amount of human annotations for full supervision, we propose the first unsupervised method,…

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality…

Autonomous Vehicles (AVs) are mostly reliant on LiDAR sensors which enable spatial perception of their surroundings and help make driving decisions. Recent works demonstrated attacks that aim to hide objects from AV perception, which can…

We consider the problem of object recognition in 3D using an ensemble of attribute-based classifiers. We propose two new concepts to improve classification in practical situations, and show their implementation in an approach implemented…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation…

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…

Contrastive learning is an essential method in self-supervised learning. It primarily employs a multi-branch strategy to compare latent representations obtained from different branches and train the encoder. In the case of multi-modal…

Currently, existing state-of-the-art 3D object detectors are in two-stage paradigm. These methods typically comprise two steps: 1) Utilize a region proposal network to propose a handful of high-quality proposals in a bottom-up fashion. 2)…

3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving, enabling precise scene understanding through point-wise classification. While unsupervised domain…

3D pose transfer is a challenging generation task that aims to transfer the pose of a source geometry onto a target geometry with the target identity preserved. Many prior methods require keypoint annotations to find correspondence between…

Existing 3D object detectors encounter extreme challenges in localizing unseen 3D objects and recognizing them as unseen, which is a crucial technology in autonomous driving in the wild. To address these challenges, we propose practical…

Most 3D neural networks are trained from scratch owing to the lack of large-scale labeled 3D datasets. In this paper, we present a novel 3D pretraining method by leveraging 2D networks learned from rich 2D datasets. We propose the…

Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually. In this paper, we introduce MixCon3D, a simple yet effective…

Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain…

Point cloud salient object detection has attracted the attention of researchers in recent years. Since existing works do not fully utilize the geometry context of 3D objects, blurry boundaries are generated when segmenting objects with…