Related papers: Stitch4D: Sparse Multi-Location 4D Urban Reconstru…
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We…
Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications. Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view…
Understanding the 3D geometry of transparent objects from RGB images is challenging due to their inherent physical properties, such as reflection and refraction. To address these difficulties, especially in scenarios with sparse views and…
We introduce a novel method to obtain high-quality 3D reconstructions from consumer RGB-D sensors. Our core idea is to simultaneously optimize for geometry encoded in a signed distance field (SDF), textures from automatically-selected…
We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the…
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…
We present One4D, a unified framework for 4D generation and reconstruction that produces dynamic 4D content as synchronized RGB frames and pointmaps. By consistently handling varying sparsities of conditioning frames through a Unified…
We propose a novel technique to register sparse 3D scans in the absence of texture. While existing methods such as KinectFusion or Iterative Closest Points (ICP) heavily rely on dense point clouds, this task is particularly challenging…
Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. However, scalability brings challenges of drift in pose estimation, introducing significant errors in the accumulated model.…
We aim to tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM). The sparse-view setting is ill-posed and underconstrained, especially for scenes where the camera rotates 360 degrees around a…
This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore,…
Highly multiplexed microscopy enables rich spatial characterization of tissues at single-cell resolution, yet most analyses rely on two-dimensional sections despite inherently three-dimensional tissue organization. Acquiring dense…
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…
Recent works in hand-object reconstruction mainly focus on the single-view and dense multi-view settings. On the one hand, single-view methods can leverage learned shape priors to generalise to unseen objects but are prone to inaccuracies…
Spatial synchronization in roadside scenarios is essential for integrating data from multiple sensors at different locations. Current methods using cascading spatial transformation (CST) often lead to cumulative errors in large-scale…
This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising…
4D medical images, which represent 3D images with temporal information, are crucial in clinical practice for capturing dynamic changes and monitoring long-term disease progression. However, acquiring 4D medical images poses challenges due…
Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD)…
Photo-realistic scene reconstruction from sparse-view, uncalibrated images is highly required in practice. Although some successes have been made, existing methods are either Sparse-View but require accurate camera parameters (i.e.,…
3D occupancy and scene flow offer a detailed and dynamic representation of 3D scene. Recognizing the sparsity and complexity of 3D space, previous vision-centric methods have employed implicit learning-based approaches to model spatial and…