Related papers: Uncertainty-aware 3D Object-Level Mapping with Dee…

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on…

Generalizable perception is one of the pillars of high-level autonomy in space robotics. Estimating the structure and motion of unknown objects in dynamic environments is fundamental for such autonomous systems. Traditionally, the solutions…

Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural…

We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map…

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

Object-level mapping builds a 3D map of objects in a scene with detailed shapes and poses from multi-view sensor observations. Conventional methods struggle to build complete shapes and estimate accurate poses due to partial occlusions and…

Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. A key step toward developing trustworthy COD systems is the…

We propose a novel learning-based approach for robust 3D shape matching. Our method builds upon deep functional maps and can be trained in a fully unsupervised manner. Previous deep functional map methods mainly focus on predicting…

Prior methods that tackle the problem of generalizable object pose estimation highly rely on having dense views of the unseen object. By contrast, we address the scenario where only a single reference view of the object is available. Our…

Object pose estimation, crucial in computer vision and robotics applications, faces challenges with the diversity of unseen categories. We propose a zero-shot method to achieve category-level 6-DOF object pose estimation, which exploits…

Estimating 6D poses and reconstructing 3D shapes of objects in open-world scenes from RGB-depth image pairs is challenging. Many existing methods rely on learning geometric features that correspond to specific templates while disregarding…

Deep unrolling is an emerging deep learning-based image reconstruction methodology that bridges the gap between model-based and purely deep learning-based image reconstruction methods. Although deep unrolling methods achieve…

We propose a method for in-hand 3D scanning of an unknown object with a monocular camera. Our method relies on a neural implicit surface representation that captures both the geometry and the appearance of the object, however, by contrast…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

Neural implicit representation has attracted attention in 3D reconstruction through various success cases. For further applications such as scene understanding or editing, several works have shown progress towards object compositional…

Object detection is one of the most important and fundamental aspects of computer vision tasks, which has been broadly utilized in pose estimation, object tracking and instance segmentation models. To obtain training data for object…

Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…

Shape completion networks have been used recently in real-world robotic experiments to complete the missing/hidden information in environments where objects are only observed in one or few instances where self-occlusions are bound to occur.…

Aleatoric uncertainty is an intrinsic property of ill-posed inverse and imaging problems. Its quantification is vital for assessing the reliability of relevant point estimates. In this paper, we propose an efficient framework for…

In robotic applications, a key requirement for safe and efficient motion planning is the ability to map obstacle-free space in unknown, cluttered 3D environments. However, commodity-grade RGB-D cameras commonly used for sensing fail to…