Related papers: LivePose: Online 3D Reconstruction from Monocular …

This work addresses the task of dense 3D reconstruction of a complex dynamic scene from images. The prevailing idea to solve this task is composed of a sequence of steps and is dependent on the success of several pipelines in its execution.…

We present Deblur-SLAM, a robust RGB SLAM pipeline designed to recover sharp reconstructions from motion-blurred inputs. The proposed method bridges the strengths of both frame-to-frame and frame-to-model approaches to model sub-frame…

In this paper, we present a tightly-coupled visual-inertial object-level multi-instance dynamic SLAM system. Even in extremely dynamic scenes, it can robustly optimise for the camera pose, velocity, IMU biases and build a dense 3D…

We present FlashSLAM, a novel SLAM approach that leverages 3D Gaussian Splatting for efficient and robust 3D scene reconstruction. Existing 3DGS-based SLAM methods often fall short in sparse view settings and during large camera movements…

Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D…

Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth…

Visual localization aims to determine the camera pose of a query image relative to a database of posed images. In recent years, deep neural networks that directly regress camera poses have gained popularity due to their fast inference…

Over the last two decades, deep learning has transformed the field of computer vision. Deep convolutional networks were successfully applied to learn different vision tasks such as image classification, image segmentation, object detection…

Accurate and reliable human motion reconstruction is crucial for creating natural interactions of full-body avatars in Virtual Reality (VR) and entertainment applications. As the Metaverse and social applications gain popularity, users are…

Depth ambiguity and joint uncertainty are the two main obstacles in obtaining accurate human pose predictions by 2D-to-3D lifting methods proposed in the literature. In particular, these issues are caused by 2D joint locations that can be…

3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since -- without…

Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance significantly degrades in dynamic environments. This…

Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two…

Conventional SLAM techniques strongly rely on scene rigidity to solve data association, ignoring dynamic parts of the scene. In this work we present Semi-Direct DefSLAM (SD-DefSLAM), a novel monocular deformable SLAM method able to map…

We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption that fails in practice as objects deviate from their canonical shapes due to wear, impact, or…

Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…

3-D pose estimation of instruments is a crucial step towards automatic scene understanding in robotic minimally invasive surgery. Although robotic systems can potentially directly provide joint values, this information is not commonly…

In recent years, considerable progress has been made for the task of rigid object pose estimation from a single RGB-image, but achieving robustness to partial occlusions remains a challenging problem. Pose refinement via rendering has shown…

In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach…

A framework for online simultaneous localization, mapping and self-calibration is presented which can detect and handle significant change in the calibration parameters. Estimates are computed in constant-time by factoring the problem and…