Darswin: Distortion aware radial swin transformer
A Athwale, A Afrasiyabi, J Lagüe… - Proceedings of the …, 2023 - openaccess.thecvf.com
Wide-angle lenses are commonly used in perception tasks requiring a large field of view.
Unfortunately, these lenses produce significant distortions making conventional models that …
Unfortunately, these lenses produce significant distortions making conventional models that …
Obstacle Avoidance of a UAV Using Fast Monocular Depth Estimation for a Wide Stereo Camera
In this study, we designed an obstacle avoidance algorithm for a quadrotor unmanned aerial
vehicle (UAV) equipped with a wide field-of-view (FOV) stereo camera, utilizing a learning …
vehicle (UAV) equipped with a wide field-of-view (FOV) stereo camera, utilizing a learning …
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds
on the previous work VPD which paved the way to use the Stable Diffusion network for …
on the previous work VPD which paved the way to use the Stable Diffusion network for …
DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture
Wide-angle fisheye images are becoming increasingly common for perception tasks in
applications such as robotics, security, and mobility (eg drones, avionics). However, current …
applications such as robotics, security, and mobility (eg drones, avionics). However, current …
VPOcc: Exploiting Vanishing Point for Monocular 3D Semantic Occupancy Prediction
Monocular 3D semantic occupancy prediction is becoming important in robot vision due to
the compactness of using a single RGB camera. However, existing methods often do not …
the compactness of using a single RGB camera. However, existing methods often do not …