Related papers: Open-Vocabulary Octree-Graph for 3D Scene Understa…
As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments,it is…
Recent open-vocabulary robot mapping methods enrich dense geometric maps with pre-trained visual-language features. While these maps allow for the prediction of point-wise saliency maps when queried for a certain language concept,…
Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robots, acquire sequences of 3D range scans ("frames"). Each frame covers the scene sparsely, due to limited angular scanning resolution and occlusion. The sparsity…
Lidar datasets are becoming more and more common. They are appreciated for their precise 3D nature, and have a wide range of applications, such as surface reconstruction, object detection, visualisation, etc. For all this applications,…
We propose an efficient and interpretable scene graph generator. We consider three types of features: visual, spatial and semantic, and we use a late fusion strategy such that each feature's contribution can be explicitly investigated. We…
Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work, SI Maps (Nanwani L, Agarwal A, Jain K, et al. Instance-level semantic…
This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs). Scene-LLM adopts a hybrid 3D…
Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined…
Recent advances in localized implicit functions have enabled neural implicit representation to be scalable to large scenes. However, the regular subdivision of 3D space employed by these approaches fails to take into account the sparsity of…
Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields,…
Point clouds and high-resolution 3D data have become increasingly important in various fields, including surveying, construction, and virtual reality. However, simply having this data is not enough; to extract useful information, semantic…
Despite monocular 3D object detection having recently made a significant leap forward thanks to the use of pre-trained depth estimators for pseudo-LiDAR recovery, such two-stage methods typically suffer from overfitting and are incapable of…
3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descriptions, and lifting them directly to a point cloud is a new and…
3D semantic occupancy prediction offers an intuitive and efficient scene understanding and has attracted significant interest in autonomous driving perception. Existing approaches either rely on full supervision, which demands costly…
Scene understanding plays a critical role in enabling intelligence and autonomy in robotic systems. Traditional approaches often face challenges, including occlusions, ambiguous boundaries, and the inability to adapt attention based on…
Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they…
Open-vocabulary semantic mapping enables robots to spatially ground previously unseen concepts without requiring predefined class sets. Current training-free methods commonly rely on multi-view fusion of semantic embeddings into a 3D map,…
Open-Vocabulary Detection (OVD) is the task of detecting all interesting objects in a given scene without predefined object classes. Extensive work has been done to deal with the OVD for 2D RGB images, but the exploration of 3D OVD is still…
Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches…
Open-vocabulary 3D occupancy is vital for embodied agents, which need to understand complex indoor environments where semantic categories are abundant and evolve beyond fixed taxonomies. While recent work has explored open-vocabulary…