17 accepted papers
We present a Bayesian Neural Radiance Field (NeRF), which explicitly quantifies uncertainty in the volume density by modeling uncertainty in the occupancy, without the need for additional networks, making it particularly suited for challenging observations and uncontrolled image environments. NeRF d…
We propose GSO-SLAM, a real-time monocular dense SLAM system that leverages Gaussian scene representation. Unlike existing methods that couple tracking and mapping with a unified scene, incurring computational costs, or loosely integrate them with well-structured tracking frameworks, introducing red
Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to interpret and follow natural language instructions without requiring labeling. However, existing methods that explicitly store language vectors in grid or node-based maps struggle to scale to large …
In this paper, we introduce a novel approach for modeling a memory-efficient spatial representation with 3D Gaussian splatting. Efficient vision-based spatial representation poses a significant challenge due to the memory demands of visual information. Recent advances in 3D rendering technologies, s
In this paper, we introduce a novel approach for modeling a memory-efficient spatial representation with 3D Gaussian splatting. Efficient vision-based spatial representation poses a significant challenge due to the memory demands of visual information. Recent advances in 3D rendering technologies, s…
Path planning in large-scale, complex 3D environments is fundamentally constrained by a trade-off between path quality and computational speed. This paper presents RUSH (Recursive and Scalable 3D <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Coarse
Path planning in large-scale, complex 3D environments is fundamentally constrained by a trade-off between path quality and computational speed. This paper presents RUSH (Recursive and Scalable 3D Coarse To Fine Path Planning), a hierarchical framework that resolves this trade-off. RUSH decomposes th…
Implicit Neural Representation (INR)-based SLAM has a critical issue where all keyframes must be stored in memory for post-training whenever a remapping is needed due to the neural network's weights themselves representing the map. To address this, previous INR-based SLAM proposed methods to modify …
We present a Bayesian Neural Radiance Field (NeRF), which explicitly quantifies uncertainty in the volume density by modeling uncertainty in the occupancy, without the need for additional networks, making it particularly suited for challenging observations and uncontrolled image environments. NeRF d
Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to interpret and follow natural language instructions without requiring labeling. However, existing methods that explicitly store language vectors in grid or node-based maps struggle to scale to large
Implicit Neural Representation (INR)-based SLAM has a critical issue where all keyframes must be stored in memory for post-training whenever a remapping is needed due to the neural network's weights themselves representing the map. To address this, previous INR-based SLAM proposed methods to modify
With the advent of Neural Radiance Field (NeRF), representing 3D scenes through multiple observations has shown significant improvements. Since this cutting-edge technique can obtain high-resolution renderings by interpolating dense 3D environments, various approaches have been proposed to apply NeR…
In this paper, we introduce a new method that first utilizes 3D Gaussian splatting in street-level localization problem. Robust localization with street-level real-world images such as street view is a major issue for autonomous vehicle, augmented reality (AR) navigation, and outdoor mobile robots.…
For effective human-robot teaming, it is important for the robots to be able to share their visual perception with the human operators. In a harsh remote collaboration setting, data compression techniques such as autoencoder can be utilized to obtain and transmit the data in terms of latent variable
Visual perception of the objects in a 3D environment is a key to successful performance in autonomous driving and simultaneous localization and mapping (SLAM). In this letter, we present a real time approach for estimating the distances to multiple objects in a scene using only a single-shot image.
In this letter, we propose a method that can be used to regenerate the 3-D normal distributions transform (NDT) for target lattice. When a pose is updated by simultaneous localization and mapping (SLAM), the lattice at the pose is also transformed. Given that NDT is a Gaussian mixture model generate
To overcome the absence of training data for unseen classes, conventional zero-shot learning approaches mainly train their model on seen datapoints and leverage the semantic descriptions for both seen and unseen classes. Beyond exploiting relations between classes of seen and unseen, we present a de…