Related papers: Self-supervised Neural Articulated Shape and Appea…
We present a methodology to model articulated objects using a sparse set of images with unknown poses. Current methods require dense multi-view observations and ground-truth camera poses. Our approach operates with as few as four views per…
We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild. Unlike prior approaches that rely on pre-defined category-specific 3D templates or…
Recent self-supervised learning models simulate the development of semantic object representations by training on visual experience similar to that of toddlers. However, these models ignore the foveated nature of human vision with high/low…
We address the task of simultaneous part-level reconstruction and motion parameter estimation for articulated objects. Given two sets of multi-view images of an object in two static articulation states, we decouple the movable part from the…
Our work aims to reconstruct hand-held objects given a single RGB image. In contrast to prior works that typically assume known 3D templates and reduce the problem to 3D pose estimation, our work reconstructs generic hand-held object…
Articulated objects are ubiquitous and important in robotics, AR/VR, and digital twins. Most self-supervised methods for articulated object modeling reconstruct discrete interaction states and relate them via cross-state geometric…
We propose an end-to-end trainable, cross-category method for reconstructing multiple man-made articulated objects from a single RGBD image, focusing on part-level shape reconstruction and pose and kinematics estimation. We depart from…
Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because…
Articulation modeling enables robots to learn joint parameters of articulated objects for effective manipulation which can then be used downstream for skill learning or planning. Existing approaches often rely on prior knowledge about the…
Traditional approaches for manipulation planning rely on an explicit geometric model of the environment to formulate a given task as an optimization problem. However, inferring an accurate model from raw sensor input is a hard problem in…
When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what…
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses discrete…
Learning generalizable visual representations from Internet data has yielded promising results for robotics. Yet, prevailing approaches focus on pre-training 2D representations, being sub-optimal to deal with occlusions and accurately…
With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise…
As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…
Reconstructing 3D geometry and appearance from a sparse set of fixed cameras is a foundational task with broad applications, yet it remains fundamentally constrained by the limited viewpoints. We show that this bound can be broken by…
In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since…
A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D…
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…
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…