Related papers: ReScene4D: Temporally Consistent Semantic Instance…
When exploring new areas, robotic systems generally exclusively plan and execute controls over geometry that has been directly measured. When entering space that was previously obstructed from view such as turning corners in hallways or…
Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many…
This paper addresses the problem of dynamic scene surface reconstruction using Gaussian Splatting (GS), aiming to recover temporally consistent geometry. While existing GS-based dynamic surface reconstruction methods can yield superior…
Reconstructing urban scenes is challenging due to their complex geometries and the presence of potentially dynamic objects. 3D Gaussian Splatting (3DGS)-based methods have shown strong performance, but existing approaches often incorporate…
Interactive segmentation has an important role in facilitating the annotation process of future LiDAR datasets. Existing approaches sequentially segment individual objects at each LiDAR scan, repeating the process throughout the entire…
We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines explicit semantic correspondences with multi-view consistency…
3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensive, manual 3D annotations. We propose UnScene3D, the first…
Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization…
Physics-driven 4D dynamic simulation from static 3D scenes remains constrained by an overlooked contradiction: reliable motion supervision often relies on online video diffusion or optical-flow pipelines whose computational cost exceeds…
Scene graphs enhance 3D mapping capabilities in robotics by understanding the relationships between different spatial elements, such as rooms and objects. Recent research extends scene graphs to hierarchical layers, adding and leveraging…
Unsupervised online 3D instance segmentation is a fundamental yet challenging task, as it requires maintaining consistent object identities across LiDAR scans without relying on annotated training data. Existing methods, such as UNIT, have…
Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing…
We present Tensor4D, an efficient yet effective approach to dynamic scene modeling. The key of our solution is an efficient 4D tensor decomposition method so that the dynamic scene can be directly represented as a 4D spatio-temporal tensor.…
3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful approach, combining explicit modeling…
The availability of high-speed 3D video sensors has greatly facilitated 3D shape acquisition of dynamic and deformable objects, but high frame rate 3D reconstruction is always degraded by spatial noise and temporal fluctuations. This paper…
As capturing devices become common, 3D scans of interior spaces are acquired on a daily basis. Through scene comparison over time, information about objects in the scene and their changes is inferred. This information is important for…
Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address…
Simultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic…
Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to…
Indoor scenes are usually characterized by scattered objects and their relationships, which turns the indoor scene classification task into a challenging computer vision task. Despite the significant performance boost in classification…