Search Results for author:
Found 12 papers, 9 papers with code
RecDiffusion: Rectangling for Image Stitching with Diffusion Models
Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing.
HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions
Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets.
Supervised Homography Learning with Realistic Dataset Generation
In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network.
Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions
On one hand, this "one-image-one-network" learning ensures complete patient privacy as it does not use any images from other patients as the training data.
GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning
Second, we design a self-guided fusion module (SGF) to fuse the background motion extracted from the gyro field with the optical flow and guide the network to focus on motion details.
DAS: Neural Architecture Search via Distinguishing Activation Score
NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer.
Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint
Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field.
Register Variation Remains Stable Across 60 Languages
In this paper, the universality and robustness of register variation is tested by comparing variation within vs. between register-specific corpora in 60 languages using corpora produced in comparable communicative situations: tweets and Wikipedia articles.
Corpus Similarity Measures Remain Robust Across Diverse Languages
This paper experiments with frequency-based corpus similarity measures across 39 languages using a register prediction task.
Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures
The goal is to use corpus similarity measures before training to predict properties of embeddings after training.
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
Experiments show that our method outperforms the state-of-art methods in both regular and challenging scenes.
DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation
In this work, we propose a deep network that compensates the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the OIS cameras.
