Related papers: Seeing Through the Grass: Semantic Pointcloud Filt…
Point cloud semantic segmentation can significantly enhance the perception of an intelligent agent. Nevertheless, the discriminative capability of the segmentation network is influenced by the quantity of samples available for different…
Robust scene representation is essential for autonomous systems to safely operate in challenging low-visibility environments. Radar has a clear advantage over cameras and lidars in these conditions due to its resilience to environmental…
Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query…
Hyperspectral video (HSV) offers valuable spatial, spectral, and temporal information simultaneously, making it highly suitable for handling challenges such as background clutter and visual similarity in object tracking. However, existing…
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms…
Accurate identification of deforestation from satellite images is essential in order to understand the geographical situation of an area. This paper introduces a new distributed approach to identify as well as locate deforestation across…
The ability to perform locomotion in various terrains is critical for legged robots. However, the robot has to have a better understanding of the surface it is walking on to perform robust locomotion on different terrains. Animals and…
Due to its robust and precise distance measurements, LiDAR plays an important role in scene understanding for autonomous driving. Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations, which are…
Semantic scene understanding, including the perception and classification of moving agents, is essential to enabling safe and robust driving behaviours of autonomous vehicles. Cameras and LiDARs are commonly used for semantic scene…
We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction. Given a stream of posed depth images from a moving camera, it trains a randomly initialised neural network to map input 3D coordinate to…
Neural implicit reconstruction via volume rendering has demonstrated its effectiveness in recovering dense 3D surfaces. However, it is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with…
Many autonomous systems forecast aspects of the future in order to aid decision-making. For example, self-driving vehicles and robotic manipulation systems often forecast future object poses by first detecting and tracking objects. However,…
With the advancement of remote-sensed imaging large volumes of very high resolution land cover images can now be obtained. Automation of object recognition in these 2D images, however, is still a key issue. High intra-class variance and low…
In recent years, computer vision has transformed fields such as medical imaging, object recognition, and geospatial analytics. One of the fundamental tasks in computer vision is semantic image segmentation, which is vital for precise object…
Self-supervised depth estimation has made a great success in learning depth from unlabeled image sequences. While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and…
Semantic segmentation is a crucial task for robot navigation and safety. However, it requires huge amounts of pixelwise annotations to yield accurate results. While recent progress in computer vision algorithms has been heavily boosted by…
Soil moisture (SM) plays a critical role in hydrological and meteorological processes. High-resolution SM can be obtained by combining coarse passive microwave data with fine-scale auxiliary variables. However, the inversion of SM at the…
3D decomposition/segmentation still remains a challenge as large-scale 3D annotated data is not readily available. Contemporary approaches typically leverage 2D machine-generated segments, integrating them for 3D consistency. While the…
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…
Estimating building footprint maps from geospatial data is of paramount importance in urban planning, development, disaster management, and various other applications. Deep learning methodologies have gained prominence in building…