Image Stitching and Rectification for Hand-Held Cameras

Variables effecting photomosaic reconstruction and ortho-rectification from aerial survey datasets

Unmanned aerial vehicles now make it possible to obtain high quality aerial imagery at a low cost, but processing those images into a single, useful entity is neither simple nor seamless. Specifically, there are factors that must be addressed when merging multiple images into a single coherent one. While ortho-rectification can be done, it tends to be expensive and time consuming. Image stitching offers a more economical, low-tech approach. However direct application tends to fail for low-elevation imagery due to one or more factors including insufficient keypoints, parallax issues, and homoge…

Document Rectification and Illumination Correction using a Patch-based CNN

We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image patches rather than the entire image. We then present a robust technique to stitch the patch results into the rectified document by processing in the gradient domain. Furthermore, we propose a second network to correct the uneven illumination, further improving the readability and OCR accuracy. Due to the less complex distortion present on the smaller image patch…

Light field Rectification based on relative pose estimation

Hand-held light field (LF) cameras have unique advantages in computer vision such as 3D scene reconstruction and depth estimation. However, the related applications are limited by the ultra-small baseline, e.g., leading to the extremely low depth resolution in reconstruction. To solve this problem, we propose to rectify LF to obtain a large baseline. Specifically, the proposed method aligns two LFs captured by two hand-held LF cameras with a random relative pose, and extracts the corresponding row-aligned sub-aperture images (SAIs) to obtain an LF with a large baseline. For an accurate rectifi…

Unfolder：对半折叠产生折痕的文档的快速定位与图像校正

Unfolder: Fast localization and image rectification of a document with a crease from folding in half

针对带对半折叠折痕的文档图像校正难题，提出专用方法Unfolder，其抗投影失真、折痕处无碎片化，新建含1600张图像的折叠文档数据集，实验显示其识别错误率和运行速度均优于主流神经网络方法。

HandAnthro：基于单张图像的手部自动人体测量

HandAnthro: Automated Hand Anthropometry from a Single Image

HandAnthro从单张手掌照片自动估计44个手部尺寸，结合YOLO姿态模型与几何轮廓细化关键点，在受控实验中达到3.80毫米平均误差，并验证了现场可行性。