Related papers: STORM: Spatio-Temporal Reconstruction Model for La…
Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative answer with 4D-LRM, the first large-scale 4D reconstruction…
The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…
Accurate and robust 3D scene reconstruction from casual, in-the-wild videos can significantly simplify robot deployment to new environments. However, reliable camera pose estimation and scene reconstruction from such unconstrained videos…
Floorplan reconstruction provides structural priors essential for reliable indoor robot navigation and high-level scene understanding. However, existing approaches either require time-consuming offline processing with a complete map, or…
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…
3D Gaussian splatting has emerged as an expressive scene representation for RGB-D visual SLAM, but its application to large-scale, multi-agent outdoor environments remains unexplored. Multi-agent Gaussian SLAM is a promising approach to…
Modeling complex rigid motion across large spatiotemporal spans remains an unresolved challenge in dynamic reconstruction. Existing paradigms are mainly confined to short-term, small-scale deformation and offer limited consideration for…
Deformable 3D Gaussian Splatting (3D-GS) is limited by missing intermediate motion information due to the low temporal resolution of RGB cameras. To address this, we introduce the first approach combining event cameras, which capture…
This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D…
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…
Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latency and memory constraints. Yet most dynamic reconstruction…
This paper presents an approach for reconstruction of 4D temporally coherent models of complex dynamic scenes. No prior knowledge is required of scene structure or camera calibration allowing reconstruction from multiple moving cameras.…
Reconstructing dynamic humans together with static scenes from monocular videos remains difficult, especially under fast motion, where RGB frames suffer from motion blur. Event cameras exhibit distinct advantages, e.g., microsecond temporal…
Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or…
In this work we investigate stochastic non-convex optimization problems where the objective is an expectation over smooth loss functions, and the goal is to find an approximate stationary point. The most popular approach to handling such…
We introduce Gaussian-Flow, a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the prevalent NeRF-based approaches hampered by slow training…
Image generative models have made significant progress in generating realistic and diverse images, supported by comprehensive guidance from various evaluation metrics. However, current video generative models struggle to generate even short…
Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes to the scene goes up as the capture time increases. These…
We present Real-time Gaussian SLAM (RTG-SLAM), a real-time 3D reconstruction system with an RGBD camera for large-scale environments using Gaussian splatting. The system features a compact Gaussian representation and a highly efficient…
Predicting spatio-temporal traffic flow presents significant challenges due to complex interactions between spatial and temporal factors. Existing approaches often address these dimensions in isolation, neglecting their critical…