Rong Xie

Latest

• Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views
• Diff-Restorer: Unleashing Visual Prompts for Diffusion-Based Universal Image Restoration
• Hdrtvformer: Efficient Sdrtv-to-Hdrtv via Affine Transformation and Spatial-Aware Transformer
• MRIR: Integrating Multimodal Insights for Diffusion-Based Realistic Image Restoration
• Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior
• No-Reference Quality Assessment of Text-to-Image Generation
• Pioneer: Offline Reinforcement Learning Based Bandwidth Estimation for Real-Time Communication
• Real-Time Free Viewpoint Video Synthesis System Based on DIBR and a Depth Estimation Network
• 360-Degree Panorama Generation from Few Unregistered NFoV Images
• Achieving Privacy-Preserving Multi-View Consistency with Advanced 3D-aware Face de-Identification
• Boosting Video Object Segmentation via Space-Time Correspondence Learning
• Deep Online Video Stabilization Using IMU Sensors
• Divide and Conquer: A Two-Step Method for High Quality Face de-Identification with Model Explainability
• Dual-Head Fusion Network for Image Enhancement
• Efficient Human Rendering with Geometric and Semantic Priors
• High-Fidelity Face Reenactment via Identity-Matched Correspondence Learning
• High-Fidelity Free-View Talking Head Synthesis for Low-Bandwidth Video Conference
• Learning Dense UV Completion for Human Mesh Recovery
• Local Bidirection Recurrent Network for Efficient Video Deblurring with the Fused Temporal Merge Module
• Multi-Scale-Based Joint Super-Resolution and Inverse Tone-Mapping with Data Synthesis for UHD HDR Video
• NeRF-SDP: Efficient Generalizable Neural Radiance Field with Scene Depth Perception
• Old-Photo Restoration with Detail- and Structure-Enhanced Cascaded Learning
• PACC: Perception Aware Congestion Control for Real-Time Communication
• Edge-Based Video Compression Texture Synthesis Using Generative Adversarial Network
• A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution
• A Large-Scale Sports Tracking Dataset and Progressive Re-Detection Based Sports Tracking
• Generative Compression for Face Video: A Hybrid Scheme
• Generative Compression for Face Video: A Hybrid Scheme
• Hiding among Your Neighbors: Face Image Privacy Protection with Differential Private k-Anonymity
• IdentityDP: Differential Private Identification Protection for Face Images
• IdentityDP: Differential Private Identification Protection for Face Images
• IdentityMask: Deep Motion Flow Guided Reversible Face Video de-Identification
• L0 Structure-Prior Assisted Blur-Intensity Aware Efficient Video Deblurring
• Multiview Nonlinear Discriminant Structure Learning for Emotion Recognition
• Perceptual Video Coding Based on Semantic-Guided Texture Detection and Synthesis
• PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer towards Video Object Detection
• PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection
• Ultra-Low Latency, Stable, and Scalable Video Transmission for Free-Viewpoint Video Services
• Dense 3D Coordinate Code Prior Guidance for High-Fidelity Face Swapping and Face Reenactment
• Modeling Acceleration Properties for Flexible INTRA HEVC Complexity Control
• 3D-BitNet: Flow-Agnostic and Precise Network for video Bit-Depth Expansion
• Video Enhancement Based on Unpaired Learning
• HEVC VMAF-oriented Perceptual Rate Distortion Optimization using CNN
• IdentityDP: Differential Private Identification Protection for Face Images
• An Elastic System Architecture for Edge Based Low Latency Interactive Video Applications
• Blindly Predict Image and Video Quality in the Wild
• Buffer Displacement Based Online Learning Algorithm For Low Latency HTTP Adaptive Streaming
• Configurable Low Delay Congestion Control Scheme for Cellular Networks
• Current Frame Priors Assisted Neural Network for Intra Prediction
• Deep Face Swapping via Cross-Identity Adversarial Training
• Deep Motion Flow Aided Face Video De-identification
• Learning a No Reference Quality Assessment Metric for Encoded 4K-UHD Video
• Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation
• Region-Aware Adaptive Instance Normalization for Image Harmonization
• VMAF Oriented Perceptual Coding Based on Piecewise Metric Coupling
• A Hybrid Model for Natural Face De-Identiation with Adjustable Privacy
• Deep Blind Video Quality Assessment for User Generated Videos
• Quality of Experience Evaluation for Streaming Video Using CGNN
• Real-time UHD video super-resolution and transcoding on heterogeneous hardware
• A VMAF Directed Perceptual Rate Distortion Optimization for Video Coding
• Native Resolution Detection for 4K-UHD Videos
• Realistic Talking Face Synthesis With Geometry-Aware Feature Transformation
• TSGAN: A Two-Stream Generative Adversarial Network for Bit-Depth Expansion
• Learning-Based Quality Enhancement For Scalable Coded Video Over Packet Lossy Networks
• A Deep Tracking and Segmentation Approach for Soccer Videos Visual Effects
• FACT: Fused Attention for Clothing Transfer with Generative Adversarial Networks
• Toward Fine-grained Facial Expression Manipulation
• An Improved QoE Evaluation Model for HTTP Adaptive Streaming
• Deep Feature Guided Image Retargeting
• FPGA Based Video Transcoding System with 2K-4K Super-Resolution Conversion
• Identifying and Pruning Redundant Structures for Deep Neural Networks
• JND-based Perceptual Rate Distortion Optimization for AV1 Encoder
• Deep Video Inverse Tone Mapping
• Gan Based Multi-Exposure Inverse Tone Mapping
• Low-precision CNN Model Quantization based on Optimal Scaling Factor Estimation
• Viewport Prediction for Panoramic Video with Multi-CNN
• Reinforcement Learning Based Adaptive Bitrate Algorithm for Transmitting Panoramic Videos
• VMAF Oriented Perceptual Optimization for Video Coding
• Improving Semantic Style Transfer Using Guided Gram Matrices
• Motion Adaptive Intra Refresh for Low Delay HEVC Encoding
• Multi-Scale Generative Adversarial Learning for Facial Attribute Transfer
• Frame Interpolation via Refined Deep Voxel Flow
• GPU Based Motion-Compensated Frame Interpolation Acceleration for Future Video Coding
• A Generic Distributed Scheduling Algorithm for Frame Rate Up Convert Video Transcoding
• A No Reference Bitstream-Based Video Quality Assessment Model for H.265/HEVC and H.264/AVC
• A Segment Constraint ABR Algorithm for HEVC Encoder
• An MCMC based Efficient Parameter Selection Model for x265 Encoder
• Learning An Inverse Tone Mapping Network with A Generative Adversarial Regularizer
• Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer
• An Improved Real-Time Video Communication System
• Low Latency MPEG-DASH System Over HTTP 2.0 and WebSocket
• Masking Effects Based Rate Control Scheme for High Efficiency Video Coding
• Rate-mixed HEVC Tile based 360 Video Streaming System
• Video Frame Interpolation Using Recurrent Convolutional Layers
• A Generic Method to Improve No-Reference Image Blur Metric Accuracy in Video Contents
• Rate control model for high dynamic range video
• Two-stream deep encoder-decoder architecture for fully automatic video object segmentation
• Weight-based bit allocation scheme for VR videos in HEVC
• Deep Binary Representation for Efficient Image Retrieval
• The SJTU UHD 360-Degree Immersive Video Sequence Dataset
• View-Dependent Omnidirectional Video Encapsulation Using Multiple Tracks
• Lagrangian method based Rate-Distortion Optimization revisited for dependent video coding
• Deep hash learning for efficient image retrieval
• A Lightweight Distributed Media Processing System for Uhd Service
• Evaluation of No Reference Bitstream-based Video Quality Assessment Methods
• Machine learning based VP9-to-HEVC video transcoding
• Two-stream recurrent convolutional neural networks for video saliency estimation
• CNN Based Post-Processing to Improve HEVC
• Improved intra angular prediction with novel interpolation filter and boundary filter
• Review of ITU-T parametric models for compressed video quality estimation
• Review of ITU-T Parametric Models for Compressed Video Quality Estimation
• Saliency based rate control scheme for high efficiency video coding
• Shot boundary detection using convolutional neural networks
• Shot Boundary Detection Using Convolutional Neural Networks
• A Proxy-assisted DASH Live Streaming Scheme
• GPU accelerated high-quality video/image super-resolution
• A Novel Parallel-Friendly Rate Control Scheme for HEVC
• Evaluation of H.265 and H.264 for Panoramas Video under Different Map Projections
• GPU Accelerating super-resolution for converting HD to 4K
• SJTU 4K video subjective quality dataset for content adaptive bit rate estimation without encoding
• The SJTU HDR Video Sequence Dataset
• Learning based fast H.264 to H.265 transcoding
• Fast depth decision with enlarged coding block sizes for HEVC intra coding of 4K ultra-HD video
• Temporal dependent bit allocation scheme for rate control in HEVC
• Systemic view on service management in Shanghai World Expo
• CNN-Based Shot Boundary Detection and Video Annotation
• Small group people behavior analysis based on temporal recursive trajectory identification
• Which metric can predict coding gain of H.265/HEVC over H.264/AVC?
• Three aspects on solving queuing service system in Shanghai world expo
• Three Aspects on Solving Queuing Service System in Shanghai World Expo
• Shanghai World Expo and queuing service system
• Queuing problems in Shanghai World Expo, Social Dynamics
• A New Combining Prediction Method of Visitor Numbers at Shanghai Expo
• Study on the collective behaviors of queuing in the Shanghai World Expo
• Bit Allocation for Fine-Granular SNR Scalability Coding with Hierarchical B Pictures