activity
20202022
most citedUnsupervised Deep Image Stitching: Reconstructing Stitched Features to Images

287 citations · 340 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV20222 cited

Unsupervised Homography Estimation with Coplanarity-Aware GAN

Mingbo Hong, Yuhang Lu, Nianjin Ye +3

Estimating homography from an image pair is a fundamental problem in image alignment. Unsupervised learning methods have received increasing attention in this field due to their pr…

cs.CV202213 cited

Distortion-Tolerant Monocular Depth Estimation On Omnidirectional Images Using Dual-cubemap

Zhijie Shen, Chunyu Lin, Lang Nie +2

Estimating the depth of omnidirectional images is more challenging than that of normal field-of-view (NFoV) images because the varying distortion can significantly twist an object'…

cs.CV20215 cited

Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation

Lang Nie, Chunyu Lin, Kang Liao +2

Homography estimation is an important task in computer vision applications, such as image stitching, video stabilization, and camera calibration. Traditional homography estimation…

cs.CV2021287 cited

Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images

Lang Nie, Chunyu Lin, Kang Liao +2

Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-b…

cs.CV20217 cited

Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline

Lingzhi He, Hongguang Zhu, Feng Li +6

Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks. Thus, depth map super-resolution (SR)…

cs.CV20213 cited

Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow

Shangrong Yang, Chunyu Lin, Kang Liao +2

Distortion rectification is often required for fisheye images. The generation-based method is one mainstream solution due to its label-free property, but its naive skip-connection…