Related papers: 3D Cloud reconstruction through geospatially-aware…

We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without…

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…

The reconstruction of ocean subsurface temperature (OST) using satellite remote sensing data holds significant scientific value for advancing the understanding of ocean dynamics and climate variability. However, the scarcity of subsurface…

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling…

mmWave radar has been shown as an effective sensing technique in low visibility, smoke, dusty, and dense fog environment. However tapping the potential of radar sensing to reconstruct 3D object shapes remains a great challenge, due to the…

Accurate four-dimensional (4D) precipitation information is essential for understanding the Earth's energy and water cycles, yet remains observationally unresolved at global scales. Conventional theory holds that geostationary infrared…

The manual annotation for large-scale point clouds is still tedious and unavailable for many harsh real-world tasks. Self-supervised learning, which is used on raw and unlabeled data to pre-train deep neural networks, is a promising…

Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great significance to autonomous driving. Most existing 3D reconstruction methods cannot be directly applied to this problem because they are elaborately designed…

Accurately reconstructing a global spatial field from sparse data has been a longstanding problem in several domains, such as Earth Sciences and Fluid Dynamics. Historically, scientists have approached this problem by employing complex…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

Sparse-view 3D reconstruction is a major challenge in computer vision, aiming to create complete three-dimensional models from limited viewing angles. Key obstacles include: 1) a small number of input images with inconsistent information;…

Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a…

Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…

Representations are a foundational component of any modelling protocol, including on molecules and molecular solids. For tasks that depend on knowledge of both molecular conformation and 3D orientation, such as the modelling of molecular…

Enabling Large Language Models (LLMs) to interact with 3D environments is challenging. Existing approaches extract point clouds either from ground truth (GT) geometry or 3D scenes reconstructed by auxiliary models. Text-image aligned 2D…

The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser…

3D urban reconstruction of buildings from remotely sensed imagery has drawn significant attention during the past two decades. While aerial imagery and LiDAR provide higher resolution, satellite imagery is cheaper and more efficient to…

3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing…

Digital twins require continuous maintenance to meet the increasing demand for high-precision geospatial data. However, traditional coarse CityGML building models, typically derived from Airborne Laser Scanning (ALS), often exhibit…