13 accepted papers
Video flow, depth, and panoptic segmentation are fundamental to diverse robotic perception and computer vision applications. Despite recent advances in specialized approaches, several inherent limitations remain challenging: first, training and inferencing three separate models is computationally co…
Force feedback in compliant robotic grippers is essential for precise manipulation tasks but remains challenging because irregular deformation of soft materials renders traditional sensor integration impractical. Event camera has emerged as a powerful alternative to conventional vision sensors throu
We have witnessed significant progress in deep learning-based 3D vision ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However existing scene-level datasets for deep learning-based 3D vision limited to either synthetic enviro…
In this work we introduce ProMotion a unified prototypical transformer-based framework engineered to model fundamental motion tasks. ProMotion offers a range of compelling attributes that set it apart from current task-specific paradigms. 1. We adopt a prototypical perspective establishing a unified…
In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoFormer seamlessly integrates prototype learning with Transformer by thoughtfully considering motion dynamics, introducing two…
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for optical flow estimation. Compared to dominant CNN-based method…
Single image 3D face reconstruction with accurate geometric details is a critical and challenging task due to the similar appearance on the face surface and fine details in organs. In this work, we introduce a self-supervised 3D face reconstruction approach from a single image that can recover detai…
Camera calibration is a necessary prerequisite in many applications of robotics, especially in robot vision in order to obtain metric reconstruction from a 2D image. In this paper, we address the problem of calibrating from a single image of a surface of revolution (SOR) based on deep learning, in o…
Feature detection and extraction is considered to be one of the most important aspects when it comes to any computer vision application, especially the autonomous driving field that is highly dependent on it. Thermal imaging is less explored in the field of autonomous driving mainly due to the high…
Self-supervised depth estimation has recently demonstrated promising performance compared to the supervised methods on challenging indoor scenes. However, the majority of efforts mainly focus on exploiting photometric and geometric consistency via forward image warping and backward image warping, ba
This paper proposes a novel deep neural network-based method for stereo image rectification. The neural network is mainly based on the theoretical basis of epipolar constraints from multi-view geometry and intensity constraints of images, which separately describes the relationship of the correspond…
Infrared Radiation (IR) images that capture the reflected IR signals from the surrounding environment have been applied to pedestrian detection and rescue tasks, especially for thermal images reflecting the surface temperature of the objects at nighttime. However, feature detection, extraction and m
Deep neural networks have significantly enhanced the performance of various computer vision tasks, including single image depth estimation and image segmentation. However, most existing approaches handle them in supervised manners and require a large number of ground truth labels that consume extens…