Related papers: D$^2$USt3R: Enhancing 3D Reconstruction for Dynami…
Most SLAM algorithms are based on the assumption that the scene is static. However, in practice, most scenes are dynamic which usually contains moving objects, these methods are not suitable. In this paper, we introduce DymSLAM, a dynamic…
We consider the task of re-calibrating the 3D pose of a static surveillance camera, whose pose may change due to external forces, such as birds, wind, falling objects or earthquakes. Conventionally, camera pose estimation can be solved with…
Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When…
Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem…
Real-time 3D reconstruction enables fast dense mapping of the environment which benefits numerous applications, such as navigation or live evaluation of an emergency. In contrast to most real-time capable approaches, our approach does not…
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…
Dynamic scene rendering and reconstruction play a crucial role in computer vision and augmented reality. Recent methods based on 3D Gaussian Splatting (3DGS), have enabled accurate modeling of dynamic urban scenes, but for urban scenes they…
Creating large LiDAR datasets with pixel-level labeling poses significant challenges. While numerous data augmentation methods have been developed to reduce the reliance on manual labeling, these methods predominantly focus on static scenes…
Space-time adaptive processing (STAP) is an effective tool for detecting a moving target in the airborne radar system. Due to the fast-changing clutter scenario and/or non side-looking configuration, the stationarity of the training data is…
Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, existing…
We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on natural language queries - and 3D reconstruction, the process…
3D spatial perception is fundamental to generalizable robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging. Depth sensors suffer from noise and material sensitivity, while existing reconstruction models…
Depth estimation is a crucial technology in robotics. Recently, self-supervised depth estimation methods have demonstrated great potential as they can efficiently leverage large amounts of unlabelled real-world data. However, most existing…
Change detection plays a vital role in scene monitoring, exploration, and continual reconstruction. Existing 3D change detection methods often exhibit spatial inconsistency in the detected changes and fail to explicitly separate pre- and…
We present a technique for a complete 3D reconstruction of small objects moving in front of a textured background. It is a particular variation of multibody structure from motion, which specializes to two objects only. The scene is captured…
Standard 3D reconstruction pipelines assume stationary world, therefore suffer from `ghost artifacts' whenever dynamic objects are present in the scene. Recent approaches has started tackling this issue, however, they typically either only…
Traditional SLAM systems, which rely on bundle adjustment, struggle with highly dynamic scenes commonly found in casual videos. Such videos entangle the motion of dynamic elements, undermining the assumption of static environments required…
With the objective of improving the registration of LiDAR point clouds produced by kinematic scanning systems, we propose a novel trajectory adjustment procedure that leverages on the automated extraction of selected reliable 3D…
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image. Geared towards high fidelity reconstruction, several recent approaches leverage implicit surface representations and deep…
Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low…