Related papers: nvblox: GPU-Accelerated Incremental Signed Distanc…
Effective robot autonomy requires motion generation that is safe, feasible, and reactive. Current methods are fragmented: fast planners output physically unexecutable trajectories, reactive controllers struggle with high-fidelity…
Continuous maps representations, as opposed to traditional discrete ones such as grid maps, have been gaining traction in the research community. However, current approaches still suffer from high computation costs, making them unable to be…
Generating safe motion plans in real-time is a key requirement for deploying robot manipulators to assist humans in collaborative settings. In particular, robots must satisfy strict safety requirements to avoid self-damage or harming nearby…
Indoor scene reconstruction from monocular images has long been sought after by augmented reality and robotics developers. Recent advances in neural field representations and monocular priors have led to remarkable results in scene-level…
Large-scale incremental mapping is fundamental to the development of robust and reliable autonomous systems, as it underpins incremental environmental understanding with sequential inputs for navigation and decision-making. LiDAR is widely…
A good representation of a large, complex mobile robot workspace must be space-efficient yet capable of encoding relevant geometric details. When exploring unknown environments, it needs to be updatable incrementally in an online fashion.…
We present fVDB, a novel GPU-optimized framework for deep learning on large-scale 3D data. fVDB provides a complete set of differentiable primitives to build deep learning architectures for common tasks in 3D learning such as convolution,…
Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and…
Neighbour embeddings (NE) allow the representation of high dimensional datasets into lower dimensional spaces and are often used in data visualisation. In practice, accelerated approximations are employed to handle very large datasets.…
We introduce a novel approach for rendering static and dynamic 3D neural signed distance functions (SDF) in real-time. We rely on nested neighborhoods of zero-level sets of neural SDFs, and mappings between them. This framework supports…
Embodied intelligence requires precise reconstruction and rendering to simulate large-scale real-world data. Although 3D Gaussian Splatting (3DGS) has recently demonstrated high-quality results with real-time performance, it still faces…
Neural distance fields (NDF) have emerged as a powerful tool for addressing challenges in 3D computer vision and graphics downstream problems. While significant progress has been made to learn NDF from various kind of sensor data, a crucial…
Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training…
Neural Signed Distance Fields (SDFs) provide a differentiable environment representation to readily obtain collision checks and well-defined gradients for robot navigation tasks. However, updating neural SDFs as the scene evolves entails…
Autonomous safe navigation in unstructured and novel environments poses significant challenges, especially when environment information can only be provided through low-cost vision sensors. Although safe reactive approaches have been…
Dense 3D reconstruction from a stream of depth images is the key to many mixed reality and robotic applications. Although methods based on Truncated Signed Distance Function (TSDF) Fusion have advanced the field over the years, the TSDF…
Signed Distance Fields (SDFs) for surface representation are commonly generated offline and subsequently loaded into interactive applications like games. Since they are not updated every frame, they only provide a rigid surface…
Graph Neural Networks (GNNs) have garnered a lot of recent interest because of their success in learning representations from graph-structured data across several critical applications in cloud and HPC. Owing to their unique compute and…
Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact. However, city-scale continual implicit dense mapping based on sparse LiDAR input is still…
A system for live high quality surface reconstruction using a single moving depth camera on a commodity hardware is presented. High accuracy and real-time frame rate is achieved by utilizing graphics hardware computing capabilities via…