English
Related papers

Related papers: Recurrence without Recurrence: Stable Video Landma…

200 papers

Magnetic particle imaging (MPI) offers unparalleled contrast and resolution for tracing magnetic nanoparticles. A common imaging procedure calibrates a system matrix (SM) that is used to reconstruct data from subsequent scans. The ill-posed…

Image and Video Processing · Electrical Eng. & Systems 2023-09-07 Alper Güngör , Baris Askin , Damla Alptekin Soydan , Can Barış Top , Emine Ulku Saritas , Tolga Çukur

Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a stable flow estimation. However, these RNNs impose large…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Shaojie Bai , Zhengyang Geng , Yash Savani , J. Zico Kolter

Finite Scalar Quantization (FSQ) offers simplified training but suffers from residual magnitude decay in multi-stage settings, where subsequent stages receive exponentially weaker signals. We propose Robust Residual Finite Scalar…

Image and Video Processing · Electrical Eng. & Systems 2026-04-02 Xiaoxu Zhu , Xiaojie Yu , Guangchao Yao , Yiming Ren , Baoxiang Li

Facial landmark detection is an important task in computer vision with numerous applications, such as head pose estimation, expression analysis, face swapping, etc. Heatmap regression-based methods have been widely used to achieve…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Chiao-An Yang , Raymond A. Yeh

Model-based deep learning methods such as loop unrolling (LU) and deep equilibrium model}(DEQ) extensions offer outstanding performance in solving inverse problems (IP). These methods unroll the optimization iterations into a sequence of…

Machine Learning · Computer Science 2024-06-11 Peimeng Guan , Naveed Iqbal , Mark A. Davenport , Mudassir Masood

Diffusion-based generative models are extremely effective in generating high-quality images, with generated samples often surpassing the quality of those produced by other models under several metrics. One distinguishing feature of these…

Machine Learning · Computer Science 2022-10-25 Ashwini Pokle , Zhengyang Geng , Zico Kolter

There has been significant recent interest in the use of deep learning for regularizing imaging inverse problems. Most work in the area has focused on regularization imposed implicitly by convolutional neural networks (CNNs) pre-trained for…

Image and Video Processing · Electrical Eng. & Systems 2023-03-10 Zihao Zou , Jiaming Liu , Brendt Wohlberg , Ulugbek S. Kamilov

Blind face restoration from low-quality (LQ) images is a challenging task that requires not only high-fidelity image reconstruction but also the preservation of facial identity. While diffusion models like Stable Diffusion have shown…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Runyi Li , Bin Chen , Jian Zhang , Radu Timofte

Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. However, this method does not explicitly guarantee that the…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 James Thewlis , Samuel Albanie , Hakan Bilen , Andrea Vedaldi

Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential…

Machine Learning · Computer Science 2019-08-28 Anil Kag , Ziming Zhang , Venkatesh Saligrama

We develop an automated video colorization framework that minimizes the flickering of colors across frames. If we apply image colorization techniques to successive frames of a video, they treat each frame as a separate colorization task.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Thejan Wijesinghe , Chamath Abeysinghe , Chanuka Wijayakoon , Lahiru Jayathilake , Uthayasanker Thayasivam

Implicit models separate the definition of a layer from the description of its solution process. While implicit layers allow features such as depth to adapt to new scenarios and inputs automatically, this adaptivity makes its computational…

Machine Learning · Computer Science 2023-03-06 Avik Pal , Alan Edelman , Christopher Rackauckas

Recent works based on deep learning and facial priors have succeeded in super-resolving severely degraded facial images. However, the prior knowledge is not fully exploited in existing methods, since facial priors such as landmark and…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Cheng Ma , Zhenyu Jiang , Yongming Rao , Jiwen Lu , Jie Zhou

Accurate facial landmarks are essential prerequisites for many tasks related to human faces. In this paper, an accurate facial landmark detector is proposed based on cascaded transformers. We formulate facial landmark detection as a…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Hui Li , Zidong Guo , Seon-Min Rhee , Seungju Han , Jae-Joon Han

Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks…

Graphics · Computer Science 2025-06-18 Lufei Liu , Tor M. Aamodt

Being accurate, efficient, and compact is essential to a facial landmark detector for practical use. To simultaneously consider the three concerns, this paper investigates a neat model with promising detection accuracy under wild…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Xiaojie Guo , Siyuan Li , Jinke Yu , Jiawan Zhang , Jiayi Ma , Lin Ma , Wei Liu , Haibin Ling

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Daniel Zoran , Nikhil Parthasarathy , Yi Yang , Drew A Hudson , Joao Carreira , Andrew Zisserman

A deep equilibrium model (DEQ) is implicitly defined through an equilibrium point of an infinite-depth weight-tied model with an input-injection. Instead of infinite computations, it solves an equilibrium point directly with root-finding…

Machine Learning · Computer Science 2023-03-30 Zenan Ling , Xingyu Xie , Qiuhao Wang , Zongpeng Zhang , Zhouchen Lin

In this work, we contribute to video saliency research in two ways. First, we introduce a new benchmark for predicting human eye movements during dynamic scene free-viewing, which is long-time urged in this field. Our dataset, named DHF1K…

Computer Vision and Pattern Recognition · Computer Science 2018-05-29 Wenguan Wang , Jianbing Shen , Fang Guo , Ming-Ming Cheng , Ali Borji

The feasibility of variational quantum algorithms, the most popular correspondent of neural networks on noisy, near-term quantum hardware, is highly impacted by the circuit depth of the involved parametrized quantum circuits (PQCs). Higher…

Machine Learning · Computer Science 2024-11-01 Philipp Schleich , Marta Skreta , Lasse B. Kristensen , Rodrigo A. Vargas-Hernández , Alán Aspuru-Guzik