# Pixel-wise Deep Image Stitching

arXiv: https://arxiv.org/abs/2112.06171 · HTML: https://mlsanity.com/paper/2112.06171/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 12 Dec 2021.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [Context-aware Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/1803.10967/) (2018)
- [Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations](https://mlsanity.com/paper/2007.06929/) (2020)
- [Asymmetric Bilateral Motion Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2108.06815/) (2021)
- [Image Inpainting with Learnable Bidirectional Attention Maps](https://mlsanity.com/paper/1909.00968/) (2019)
- [Residual Conv-Deconv Grid Network for Semantic Segmentation](https://mlsanity.com/paper/1707.07958/) (2017)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://mlsanity.com/paper/2106.12859/) (2021)
- [Enhanced Quadratic Video Interpolation](https://mlsanity.com/paper/2009.04642/) (2020)
- [Quasi-homography warps in image stitching](https://mlsanity.com/paper/1701.08006/) (2017)
- [Learning Edge-Preserved Image Stitching from Large-Baseline Deep Homography](https://mlsanity.com/paper/2012.06194/) (2020)

## Built on by (most cited first, 4 of 4)

- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Deep Rotation Correction without Angle Prior](https://mlsanity.com/paper/2207.03054/) (2022)
- [Learning Residual Elastic Warps for Image Stitching under Dirichlet Boundary Condition](https://mlsanity.com/paper/2309.01406/) (2023)
- [Depth-Supervised Fusion Network for Seamless-Free Image Stitching](https://mlsanity.com/paper/2510.21396/) (2025)

## Abstract (arXiv)

Image stitching aims at stitching the images taken from different viewpoints into an image with a wider field of view. Existing methods warp the target image to the reference image using the estimated warp function, and a homography is one of the most commonly used warping functions. However, when images have large parallax due to non-planar scenes and translational motion of a camera, the homography cannot fully describe the mapping between two images. Existing approaches based on global or local homography estimation are not free from this problem and suffer from undesired artifacts due to parallax. In this paper, instead of relying on the homography-based warp, we propose a novel deep image stitching framework exploiting the pixel-wise warp field to handle the large-parallax problem. The proposed deep image stitching framework consists of two modules: Pixel-wise Warping Module (PWM) and Stitched Image Generating Module (SIGMo). PWM employs an optical flow estimation model to obtain pixel-wise warp of the whole image, and relocates the pixels of the target image with the obtained warp field. SIGMo blends the warped target image and the reference image while eliminating unwanted artifacts such as misalignments, seams, and holes that harm the plausibility of the stitched result. For training and evaluating the proposed framework, we build a large-scale dataset that includes image pairs with corresponding pixel-wise ground truth warp and sample stitched result images. We show that the results of the proposed framework are qualitatively superior to those of the conventional methods, especially when the images have large parallax. The code and the proposed dataset will be publicly available soon.