Related papers: S3Former: Self-supervised High-resolution Transfor…
Photovoltaic (PV) power forecasting plays a crucial role in optimizing the operation and planning of PV systems, thereby enabling efficient energy management and grid integration. However, un certainties caused by fluctuating weather…
3D world models (i.e., learning-based 3D dynamics models) offer a promising approach to generalizable robotic manipulation by capturing the underlying physics of environment evolution conditioned on robot actions. However, existing 3D world…
3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common PointNet design introduces an information bottleneck that…
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore…
Building a robust perception module is crucial for visuomotor policy learning. While recent methods incorporate pre-trained 2D foundation models into robotic perception modules to leverage their strong semantic understanding, they struggle…
Recently, multi-modal masked autoencoders (MAE) has been introduced in 3D self-supervised learning, offering enhanced feature learning by leveraging both 2D and 3D data to capture richer cross-modal representations. However, these…
Renewable energy sources are of great interest to combat global warming, yet promising sources like photovoltaic (PV) cells are not efficient and cheap enough to act as an alternative to traditional energy sources. Perovskite has high…
3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…
Transformers have demonstrated remarkable performance in natural language processing and computer vision. However, existing vision Transformers struggle to learn from limited medical data and are unable to generalize on diverse medical…
Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…
The adoption of Vision Transformers (ViTs) based architectures represents a significant advancement in 3D Medical Image (MI) segmentation, surpassing traditional Convolutional Neural Network (CNN) models by enhancing global contextual…
We formulate, solve computationally and study experimentally the problem of collecting solar energy in three dimensions(1-5). We demonstrate that absorbers and reflectors can be combined in the absence of sun tracking to build…
Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field…
Hyperspectral imaging (HSI) provides rich spectral-spatial information across hundreds of contiguous bands, enabling precise material discrimination in applications such as environmental monitoring, agriculture, and urban analysis. However,…
Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representations to generate query…
The global generation of renewable energy has rapidly increased, primarily due to the installation of large-scale renewable energy power plants. However, monitoring renewable energy assets in these large plants remains challenging due to…
Multi-person motion prediction remains a challenging problem, especially in the joint representation learning of individual motion and social interactions. Most prior methods only involve learning local pose dynamics for individual motion…
The impact of soiling on solar panels is an important and well-studied problem in renewable energy sector. In this paper, we present the first convolutional neural network (CNN) based approach for solar panel soiling and defect analysis.…
We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a…
Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge…