462 citations · 992 across the 34 of their papers we have counts for
35 papers
Optimized Adaptive Loop Filter in Versatile Video Coding
Xuewei Meng, Jiaqi Zhang, Chuanmin Jia +3
In the Versatile Video Coding~(VVC) standard, adaptive loop filter~(ALF), including Geometry transformation-based Adaptive Loop Filter~(GALF) and Cross Component Adaptive Loop Filt…
Spatio-Temporal Correlation Guided Geometric Partitioning for Versatile Video Coding
Xuewei Meng, Chuanmin Jia, Xinfeng Zhang +2
Geometric partitioning has attracted increasing attention by its remarkable motion field description capability in the hybrid video coding framework. However, the existing geometri…
Edge-directed geometric partitioning for versatile video coding
Xuewei Meng, Xinfeng Zhang, Chuanmin Jia +3
To improve the coding performance, geometric partition (GEO) was proposed for the upcoming VVC standard. GEO provides 140 partition candidates. The index of optimal GEO mode needs…
Deformable Wiener Filter for Future Video Coding
Xuewei Meng, Chuanmin Jia, Xinfeng Zhang +2
In-loop filters have attracted increasing attention due to the remarkable noise-reduction capability in the hybrid video coding framework. However, the existing in-loop filters in…
Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach
Qi Zhang, Shanshe Wang, Xinfeng Zhang +3
Nowadays, high-quality images are pursued by both humans for better viewing experience and by machines for more accurate visual analysis. However, images are usually compressed bef…
Advanced Learning-Based Inter Prediction for Future Video Coding
Yanchen Zhao, Wenhong Duan, Chuanmin Jia +2
In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in i…
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
Wenkang Shan, Zhenhua Liu, Xinfeng Zhang +5
In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for probabilistic 3D huma…
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
Qi Zhang, Shanshe Wang, Xinfeng Zhang +4
Video Coding for Machines (VCM) aims to compress visual signals for machine analysis. However, existing methods only consider a few machines, neglecting the majority. Moreover, the…
STIP: A SpatioTemporal Information-Preserving and Perception-Augmented Model for High-Resolution Video Prediction
Zheng Chang, Xinfeng Zhang, Shanshe Wang +2
Although significant achievements have been achieved by recurrent neural network (RNN) based video prediction methods, their performance in datasets with high resolutions is still…
Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution
Yuqing Liu, Qi Jia, Jian Zhang +4
As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years. The main task of SISR is to recover the information loss caused by t…
Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment
Yuqing Liu, Qi Jia, Shanshe Wang +2
Image super-resolution (SR) has been widely investigated in recent years. However, it is challenging to fairly estimate the performance of various SR methods, as the lack of reliab…
Learning Weighting Map for Bit-Depth Expansion within a Rational Range
Yuqing Liu, Qi Jia, Jian Zhang +4
Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution f…
STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond
Zheng Chang, Xinfeng Zhang, Shanshe Wang +2
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information…
STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction
Zheng Chang, Xinfeng Zhang, Shanshe Wang +2
Although many video prediction methods have obtained good performance in low-resolution (64128) videos, predictive models for high-resolution (5124K) videos have not be…
P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
Wenkang Shan, Zhenhua Liu, Xinfeng Zhang +3
This paper introduces a novel Pre-trained Spatial Temporal Many-to-One (P-STMO) model for 2D-to-3D human pose estimation task. To reduce the difficulty of capturing spatial and tem…
Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution
Yuqing Liu, Qi Jia, Xin Fan +3
It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details. Existing deep learning works almost neglect the inherent str…
Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
Kai Li, Jie Yang, Siwei Ma +4
Pixel-level road crack detection has always been a challenging task in intelligent transportation systems. Due to the external environments, such as weather, light, and other facto…
Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation
Wenkang Shan, Haopeng Lu, Shanshe Wang +2
Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints (local motion) instead…
Rate Distortion Characteristic Modeling for Neural Image Compression
Chuanmin Jia, Ziqing Ge, Shanshe Wang +2
End-to-end optimized neural image compression (NIC) has obtained superior lossy compression performance recently. In this paper, we consider the problem of rate-distortion (R-D) ch…
Visual Analysis Motivated Rate-Distortion Model for Image Coding
Zhimeng Huang, Chuanmin Jia, Shanshe Wang +1
Optimized for pixel fidelity metrics, images compressed by existing image codec are facing systematic challenges when used for visual analysis tasks, especially under low-bitrate c…
Sub-sampled Cross-component Prediction for Emerging Video Coding Standards
Junru Li, Meng Wang, Li Zhang +5
Cross-component linear model (CCLM) prediction has been repeatedly proven to be effective in reducing the inter-channel redundancies in video compression. Essentially speaking, the…
Implicit Subspace Prior Learning for Dual-Blind Face Restoration
Lingbo Yang, Pan Wang, Zhanning Gao +4
Face restoration is an inherently ill-posed problem, where additional prior constraints are typically considered crucial for mitigating such pathology. However, real-world image pr…
Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution
Yuqing Liu, Xinfeng Zhang, Shanshe Wang +2
Multi-scale design has been considered in recent image super-resolution (SR) works to explore the hierarchical feature information. Existing multi-scale networks aim to build elabo…
Region-adaptive Texture Enhancement for Detailed Person Image Synthesis
Lingbo Yang, Pan Wang, Xinfeng Zhang +6
The ability to produce convincing textural details is essential for the fidelity of synthesized person images. However, existing methods typically follow a ``warping-based'' strate…