Related papers: HOISDF: Constraining 3D Hand-Object Pose Estimatio…
This report describes our 1st place solution to ECCV 2022 challenge on Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras (hand pose estimation). In this challenge, we aim to estimate global 3D hand poses from…
Recent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense 3D points in space.…
Accurate and dense mapping in large-scale environments is essential for various robot applications. Recently, implicit neural signed distance fields (SDFs) have shown promising advances in this task. However, most existing approaches employ…
Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online…
We present a novel framework for motion planning in dynamic environments that accounts for the predicted trajectories of moving objects in the scene. We explore the use of composite signed-distance fields in motion planning and detail how…
Metric localization plays a critical role in vision-based navigation. For overcoming the degradation of matching photometry under appearance changes, recent research resorted to introducing geometry constraints of the prior scene structure.…
We propose a novel 3D spatial representation for data fusion and scene reconstruction. Probabilistic Signed Distance Function (Probabilistic SDF, PSDF) is proposed to depict uncertainties in the 3D space. It is modeled by a joint…
This paper presents a method to learn hand-object interaction prior for reconstructing a 3D hand-object scene from a single RGB image. The inference as well as training-data generation for 3D hand-object scene reconstruction is challenging…
We present KDFNet, a novel method for 6D object pose estimation from RGB images. To handle occlusion, many recent works have proposed to localize 2D keypoints through pixel-wise voting and solve a Perspective-n-Point (PnP) problem for pose…
In this work, we present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. Our workflow is based on training data and neural networks for single-view 3D…
In the field of computer vision, the numerical encoding of 3D surfaces is crucial. It is classical to represent surfaces with their Signed Distance Functions (SDFs) or Unsigned Distance Functions (UDFs). For tasks like representation…
3D geometric shape completion hinges on representation learning and a deep understanding of geometric data. Without profound insights into the three-dimensional nature of the data, this task remains unattainable. Our work addresses this…
We describe in this short note a technique to convert an implicit surface into a Signed Distance Function (SDF) while exactly preserving the zero level-set of the implicit. The proposed approach relies on embedding the input implicit in the…
Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand's high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing…
In medical and industrial domains, providing guidance for assembly processes can be critical to ensure efficiency and safety. Errors in assembly can lead to significant consequences such as extended surgery times and prolonged manufacturing…
We propose a method for hand pose estimation based on a deep regressor trained on two different kinds of input. Raw depth data is fused with an intermediate representation in the form of a segmentation of the hand into parts. This…
Estimating the 3D pose of hand and potential hand-held object from monocular images is a longstanding challenge. Yet, existing methods are specialized, focusing on either bare-hand or hand interacting with object. No method can flexibly…
We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. Our motivation is the current lack of annotated real images for…
Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale…
Rich geometric understanding of the world is an important component of many robotic applications such as planning and manipulation. In this paper, we present a modular pipeline for pose and shape estimation of objects from RGB-D images…