Related papers: 4D-ONIX: A deep learning approach for reconstructi…

Estimating the forces acting between instruments and tissue is a challenging problem for robot-assisted minimally-invasive surgery. Recently, numerous vision-based methods have been proposed to replace electro-mechanical approaches.…

Visual-LiDAR odometry is a critical component for autonomous system localization, yet achieving high accuracy and strong robustness remains a challenge. Traditional approaches commonly struggle with sensor misalignment, fail to fully…

3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in…

We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations. The segmented 3D objects are represented using separate Neural Radiance…

Image guidance for minimally invasive interventions is usually performed by acquiring fluoroscopic images using a C-arm system. However, the projective data provide only limited information about the spatial structure and position of…

Deep learning (DL) has emerged as a tool for improving accelerated MRI reconstruction. A common strategy among DL methods is the physics-based approach, where a regularized iterative algorithm alternating between data consistency and a…

The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes. Most existing solutions produce temporally uncorrelated point clouds or meshes with unknown point/vertex…

Deep learning-based, single-view depth estimation methods have recently shown highly promising results. However, such methods ignore one of the most important features for determining depth in the human vision system, which is motion. We…

Three-dimensional segmentation in magnetic resonance images (MRI), which reflects the true shape of the objects, is challenging since high-resolution isotropic MRIs are rare and typical MRIs are anisotropic, with the out-of-plane dimension…

Learning 4D language fields to enable time-sensitive, open-ended language queries in dynamic scenes is essential for many real-world applications. While LangSplat successfully grounds CLIP features into 3D Gaussian representations,…

Inverse problems spanning four or more dimensions such as space, time and other independent parameters have become increasingly important. State-of-the-art 4D reconstruction methods use model based iterative reconstruction (MBIR), but…

Single Particle Imaging techniques at X-ray lasers have made significant strides, yet the challenge of determining the orientation of freely rotating molecules during delivery remains. In this study, we propose a novel method to partially…

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…

Object reconstruction is relevant for many autonomous robotic tasks that require interaction with the environment. A key challenge in such scenarios is planning view configurations to collect informative measurements for reconstructing an…

Accurate 3D+t whole-heart mesh reconstruction from cine MRI is a clinically crucial yet technically challenging task. The difficulty of this task arises from two coupled factors: inherently sparse sampling of 3D cardiac anatomy by 2D image…

Single-pixel imaging (SPI) is significant for applications constrained by transmission bandwidth or lighting band, where 3D SPI can be further realized through capturing signals carrying depth. Sampling strategy and reconstruction algorithm…

In this paper, we present a learning based approach to depth fusion, i.e., dense 3D reconstruction from multiple depth images. The most common approach to depth fusion is based on averaging truncated signed distance functions, which was…

Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene…

Modern imaging instruments can produce terabytes to petabytes of data for a single experiment. The biggest barrier to processing big image datasets has been computational, where image analysis algorithms often lack the efficiency needed to…

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…