Related papers: Collaborative Learning for 3D Hand-Object Reconstr…
Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from the first-person point of view. An open challenge in…
Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside…
Monocular 3D reconstruction of articulated object categories is challenging due to the lack of training data and the inherent ill-posedness of the problem. In this work we use video self-supervision, forcing the consistency of consecutive…
Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are ineffective or only tackle the problem partially. In this…
In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…
This paper proposes a novel method for understanding daily hand-object manipulation by developing computer vision-based techniques. Specifically, we focus on recognizing hand grasp types, object attributes and manipulation actions within an…
We present a method for inferring diverse 3D models of human-object interactions from images. Reasoning about how humans interact with objects in complex scenes from a single 2D image is a challenging task given ambiguities arising from the…
We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos. Compared to prior work, our problem setting is more realistic yet more challenging for three reasons: 1) due to occlusion or…
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…
Reconstructing hand-held objects from monocular RGB images is an appealing yet challenging task. In this task, contacts between hands and objects provide important cues for recovering the 3D geometry of the hand-held objects. Though recent…
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…
We present an unsupervised framework for simultaneous appearance-based object discovery, detection, tracking and reconstruction using RGBD cameras and a robot manipulator. The system performs dense 3D simultaneous localization and mapping…
The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…
Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of such experience is that the learner sees the same object…
Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…
Human-object interactions with articulated objects are common in everyday life. Despite much progress in single-view 3D reconstruction, it is still challenging to infer an articulated 3D object model from an RGB video showing a person…
We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, existing approaches rely…
3D hand pose is an underexplored modality for action recognition. Poses are compact yet informative and can greatly benefit applications with limited compute budgets. However, poses alone offer an incomplete understanding of actions, as…
Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising…
Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…