Related papers: SSFlowNet: Semi-supervised Scene Flow Estimation O…

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

Floods wreak havoc throughout the world, causing billions of dollars in damages, and uprooting communities, ecosystems and economies. The NASA Impact Flood Detection competition tasked participants with predicting flooded pixels after…

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few…

FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey. The dataset presents a unique challenge of advancing the damage assessment process for post-disaster scenarios…

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real…

The proposed RMS-FlowNet++ is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation that can operate on high-density point clouds. For hierarchical scene f low estimation, existing methods rely on…

Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to…

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages…

Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable…

This work proposes a metric learning approach for self-supervised scene flow estimation. Scene flow estimation is the task of estimating 3D flow vectors for consecutive 3D point clouds. Such flow vectors are fruitful, \eg for recognizing…

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for…

Scene flow estimation is the task of describing 3D motion between temporally successive observations. This thesis aims to build the foundation for building scene flow estimators with two important properties: they are scalable, i.e. they…

Supervised learning algorithms based on Convolutional Neural Networks have become the benchmark for medical image segmentation tasks, but their effectiveness heavily relies on a large amount of labeled data. However, annotating medical…

When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many…

Scene flow is the three-dimensional (3D) motion field of a scene. It provides information about the spatial arrangement and rate of change of objects in dynamic environments. Current learning-based approaches seek to estimate the scene flow…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled…

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e.,…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…