Related papers: P-SLCR: Unsupervised Point Cloud Semantic Segmenta…
Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…
Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…
This paper presents a framework for semantic segmentation on sparse sequential point clouds of millimeter-wave radar. Compared with cameras and lidars, millimeter-wave radars have the advantage of not revealing privacy, having a strong…
Monocular Semantic Scene Completion (MSSC) aims to predict the voxel-wise occupancy and semantic category from a single-view RGB image. Existing methods adopt a single-stage framework that aims to simultaneously achieve visible region…
Recent studies on semantic communication commonly rely on neural network (NN) based transceivers such as deep joint source and channel coding (DeepJSCC). Unlike traditional transceivers, these neural transceivers are trainable using actual…
We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations. The key challenge here is the discrepancy between the target of dense per-point semantic…
Semi-supervised learning (SSL) enables training of powerful models with the assumption of limited, carefully labelled data and a large amount of unlabeled data to support the learning. In this paper, we propose a hybrid consistency learning…
Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds…
The task of Novel Class Discovery (NCD) in semantic segmentation entails training a model able to accurately segment unlabelled (novel) classes, relying on the available supervision from annotated (base) classes. Although extensively…
Unsupervised semantic segmentation aims to discover groupings within and across images that capture object and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in…
As a fundamental yet challenging problem in intelligent transportation systems, point cloud registration attracts vast attention and has been attained with various deep learning-based algorithms. The unsupervised registration algorithms…
Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels…
Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring. Although numerous deep learning methods have been proposed for point cloud…
Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most…
Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…
Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…
With the evolution of the cloud and customer centric culture, we inherently accumulate huge repositories of textual reviews, feedback, and support data.This has driven enterprises to seek and research engagement patterns, user network…
Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…
Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC)…
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is…