research
∙
03/02/2023
Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
Based on the Manhattan World assumption, most existing indoor layout est...
share
research
∙
02/20/2023
Unsupervised OmniMVS: Efficient Omnidirectional Depth Inference via Establishing Pseudo-Stereo Supervision
Omnidirectional multi-view stereo (MVS) vision is attractive for its ult...
research
∙
02/16/2023
Learning Thin-Plate Spline Motion and Seamless Composition for Parallax-Tolerant Unsupervised Deep Image Stitching
Traditional image stitching approaches tend to leverage increasingly com...
research
∙
01/04/2023
RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning
The wide-angle lens shows appealing applications in VR technologies, but...
research
∙
08/03/2022
Neural Contourlet Network for Monocular 360 Depth Estimation
For a monocular 360 image, depth estimation is a challenging because the...
research
∙
07/07/2022
Deep Rotation Correction without Angle Prior
Not everybody can be equipped with professional photography skills and s...
research
∙
07/06/2022
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation
Recently, horizontal representation-based panoramic semantic segmentatio...
research
∙
03/18/2022
Distortion-Tolerant Monocular Depth Estimation On Omnidirectional Images Using Dual-cubemap
Estimating the depth of omnidirectional images is more challenging than ...
research
∙
03/17/2022
PanoFormer: Panorama Transformer for Indoor 360° Depth Estimation
Existing panoramic depth estimation methods based on convolutional neura...
research
∙
03/08/2022
Deep Rectangling for Image Stitching: A Learning Baseline
Stitched images provide a wide field-of-view (FoV) but suffer from unple...
research
∙
12/08/2021
FPPN: Future Pseudo-LiDAR Frame Prediction for Autonomous Driving
LiDAR sensors are widely used in autonomous driving due to the reliable ...
research
∙
07/06/2021
Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation
Homography estimation is an important task in computer vision, such as i...
research
∙
06/24/2021
Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images
Traditional feature-based image stitching technologies rely heavily on f...
research
∙
12/11/2020