Related papers: NIFT: Neural Interaction Field and Template for Ob…

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However,…

Human activity recognition in videos has been widely studied and has recently gained significant advances with deep learning approaches; however, it remains a challenging task. In this paper, we propose a novel framework that simultaneously…

Real-world dexterous manipulation often encounters unexpected errors and disturbances, which can lead to catastrophic failures, such as dropping the manipulated object. To address this challenge, we focus on the problem of catching a…

Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition. While learning-based methods have surpassed traditional handcrafted…

The Vision Transformer (ViT) architecture has become widely recognized in computer vision, leveraging its self-attention mechanism to achieve remarkable success across various tasks. Despite its strengths, ViT's optimization remains…

Both indoor and outdoor environments are inherently structured and repetitive. Traditional modeling pipelines keep an asset library storing unique object templates, which is both versatile and memory efficient in practice. Inspired by this…

Automated Facial Beauty Prediction (FBP) is a challenging computer vision task due to the complex interplay of local and global facial features that influence human perception. While Convolutional Neural Networks (CNNs) excel at feature…

Image-text matching (ITM) is a fundamental problem in computer vision. The key issue lies in jointly learning the visual and textual representation to estimate their similarity accurately. Most existing methods focus on feature enhancement…

We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in…

Perceiving and manipulating 3D articulated objects (e.g., cabinets, doors) in human environments is an important yet challenging task for future home-assistant robots. The space of 3D articulated objects is exceptionally rich in their…

Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to reconstruct such non-rigid scenes is through the use of a…

Robotic manipulation tasks such as object insertion typically involve interactions between object and environment, namely extrinsic contacts. Prior work on Neural Contact Fields (NCF) use intrinsic tactile sensing between gripper and object…

We propose a framework for aligning and fusing multiple images into a single view using neural image representations (NIRs), also known as implicit or coordinate-based neural representations. Our framework targets burst images that exhibit…

We propose Neural Deformable Fields (NDF), a new representation for dynamic human digitization from a multi-view video. Recent works proposed to represent a dynamic human body with shared canonical neural radiance fields which links to the…

Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive…

Neural implicit surface representations have emerged as a promising paradigm to capture 3D shapes in a continuous and resolution-independent manner. However, adapting them to articulated shapes is non-trivial. Existing approaches learn a…

Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…

Most existing Siamese-based tracking methods execute the classification and regression of the target object based on the similarity maps. However, they either employ a single map from the last convolutional layer which degrades the…

Object pose estimation is a prominent task in computer vision. The object pose gives the orientation and translation of the object in real-world space, which allows various applications such as manipulation, augmented reality, etc. Various…

One of the fundamental goals of visual perception is to allow agents to meaningfully interact with their environment. In this paper, we take a step towards that long-term goal -- we extract highly localized actionable information related to…