541 citations · 1.5k across the 76 of their papers we have counts for
20 papers · 1 filter
Fingerprints of Super Resolution Networks
Jeremy Vonderfecht, Feng Liu
Several recent studies have demonstrated that deep-learning based image generation models, such as GANs, can be uniquely identified, and possibly even reverse-engineered, by the fi…
RHINO: Regularizing the Hash-based Implicit Neural Representation
Hao Zhu, Fengyi Liu, Qi Zhang +2
The use of Implicit Neural Representation (INR) through a hash-table has demonstrated impressive effectiveness and efficiency in characterizing intricate signals. However, current…
AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation
Hyunyoung Jung, Zhuo Hui, Lei Luo +5
To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs. However, downsizing inputs makes the esti…
Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
Chaoqi Chen, Luyao Tang, Feng Liu +3
Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one. The general objective of DG methods is to learn semant…
A Perceptual Quality Metric for Video Frame Interpolation
Qiqi Hou, Abhijay Ghildyal, Feng Liu
Research on video frame interpolation has made significant progress in recent years. However, existing methods mostly use off-the-shelf metrics to measure the quality of interpolat…
Shift-tolerant Perceptual Similarity Metric
Abhijay Ghildyal, Feng Liu
Existing perceptual similarity metrics assume an image and its reference are well aligned. As a result, these metrics are often sensitive to a small alignment error that is imperce…
A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images
Chengfeng Zhou, Songchang Chen, Chenming Xu +6
Since data scarcity and data heterogeneity are prevailing for medical images, well-trained Convolutional Neural Networks (CNNs) using previous normalization methods may perform poo…
SNeRF: Stylized Neural Implicit Representations for 3D Scenes
Thu Nguyen-Phuoc, Feng Liu, Lei Xiao
This paper presents a stylized novel view synthesis method. Applying state-of-the-art stylization methods to novel views frame by frame often causes jittering artifacts due to the…
A novel stereo matching pipeline with robustness and unfixed disparity search range
Jiazhi Liu, Feng Liu
Stereo matching is an essential basis for various applications, but most stereo matching methods have poor generalization performance and require a fixed disparity search range. Mo…
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Feng Liu, Xiaosong Zhang, Zhiliang Peng +4
Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the…
Transformer Compressed Sensing via Global Image Tokens
Marlon Bran Lorenzana, Craig Engstrom, Shekhar S. Chandra
Convolutional neural networks (CNN) have demonstrated outstanding Compressed Sensing (CS) performance compared to traditional, hand-crafted methods. However, they are broadly limit…
Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image
Feng Liu, Xiaoming Liu
Inferring 3D locations and shapes of multiple objects from a single 2D image is a long-standing objective of computer vision. Most of the existing works either predict one of these…
Escaping the Gradient Vanishing: Periodic Alternatives of Softmax in Attention Mechanism
Shulun Wang, Bin Liu, Feng Liu
Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed su…
View Synthesis of Dynamic Scenes based on Deep 3D Mask Volume
Kai-En Lin, Guowei Yang, Lei Xiao +2
Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virt…
Fast Monte Carlo Rendering via Multi-Resolution Sampling
Qiqi Hou, Zhan Li, Carl S Marshall +2
Monte Carlo rendering algorithms are widely used to produce photorealistic computer graphics images. However, these algorithms need to sample a substantial amount of rays per pixel…
Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
Feng Liu, Luan Tran, Xiaoming Liu
Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CAD-generated synth…
Deep Simultaneous Optimisation of Sampling and Reconstruction for Multi-contrast MRI
Xinwen Liu, Jing Wang, Fangfang Tang +3
MRI images of the same subject in different contrasts contain shared information, such as the anatomical structure. Utilizing the redundant information amongst the contrasts to sub…
Context-aware Synthesis for Video Frame Interpolation
Simon Niklaus, Feng Liu
Video frame interpolation algorithms typically estimate optical flow or its variations and then use it to guide the synthesis of an intermediate frame between two consecutive origi…
Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
Feng Liu, Qijun Zhao, Xiaoming Liu +1
Face alignment and 3D face reconstruction are traditionally accomplished as separated tasks. By exploring the strong correlation between 2D landmarks and 3D shapes, in contrast, we…
On 3D Face Reconstruction via Cascaded Regression in Shape Space
Feng Liu, Dan Zeng, Jing Li +1
Cascaded regression has been recently applied to reconstructing 3D faces from single 2D images directly in shape space, and achieved state-of-the-art performance. This paper invest…