jjlei@tju.edu.cn
信息与通信工程
国家优青、天津市****、天津市中青年科技创新领军人才
教授
3D视频智能编码理论与方法

---

面向大数据应用的桌面实时真三维显示技术

---

视频场景智能识别与理解

---

3D视频编码与处理

---

深度学习增强的视频帧间编码研究

---

3D视频信号处理理论与关键技术

---

基于立体视觉显著性的多视点视频编码理论与技术研究

---

中芬基于Livinglab的智慧设计创新网络平台与应用示范

---

面向多视点自由立体显示的虚拟视点生成及校正理论与技术研究

---

基于视觉注意机制的立体图像视差校正理论与技术研究

---

面向3D显示的视频处理理论与关键技术

---

******

---

立体电视图像双眼串扰测试方法研究
一种多视点立体图像零视差校正方法

---

虚拟视点绘制方法

---

基于边界控制置信传播的立体图像视差估计方法

---

一种深度视频编码方法

---

一种多视点视频编码码率控制方法

---

深度视频编码的像素级预测方法

---

一种基于多级感兴趣区域的多视点视频编码方法

---

深度视频编码的三边滤波方法

---

一种人体检测方法

---

彩色与深度视频联合编码的比特分配及码率控制算法

---

一种基于自适应权值的时域一致性深度视频估计方法

---

一种基于区域自适应模型的深度视频码率控制方法

---

一种面向单视点绘制的空洞填补方法

---

一种深度图可靠性评价测度方法

---

一种基于视点间相关性的深度视频编码算法

---

一种基于形状回归的草图图像检索方法

---

---

---

---

---

---

---

---

---

---

---

---

---

---

---

A universal framework for salient object detection,

---

Depth coding based on depth-texture motion and structure similarities,

---

Semi-heterogeneous three-way joint embedding network for sketch-based image retrieval,

---

Depth map super-resolution considering view synthesis quality,

---

Unsupervised video action clustering via motion-scene interaction constraint,

---

Person re-identification by semantic region representation and topology constraint,

---

Depth sensation enhancement for multiple virtual view rendering,

---

Fast mode decision based on grayscale similarity and inter-view correlation for depth map coding in 3D-HEVC,

---

Motion and structure information based adaptive weighted depth video estimation,

---

Region adaptive R-λ model based rate control for depth maps coding,

---

Fast mode decision using inter-view and inter-component correlations for multiview depth video coding,

---

Co-saliency detection for RGBD images based on multi-constraint feature matching and cross label propagation,

---

Fast intra prediction based on content property analysis for low complexity HEVC-based screen content coding,

---

Stereoscopic image stitching based on a hybrid warping model,

---

Review of visual saliency detection with comprehensive information,

---

Depth-preserving stereo image retargeting based on pixel fusion,

---

An iterative co-saliency framework for RGBD images,

---

Visual attention modeling for stereoscopic video: A benchmark and computational model,

---

HSCS: Hierarchical sparsity based co-saliency detection for RGBD images

---

Shape-preserving object depth control for stereoscopic images,

---

Fast motion estimation based on content property for low-complexity H.265/HEVC encoder,

---

Projection-based disparity control for toed-in multiview images,

---

Stereoscopic visual attention guided disparity control for multiview images,

---

Rate control of hierarchical B prediction structure for multi-view video coding,

---

Segmentation-based adaptive vergence control for parallel multiview stereoscopic images,

---

Saliency detection for stereoscopic images based on depth confidence analysis and multiple cues fusion,

---

Multilevel region of interest guided bit allocation for multiview video coding,

---

Pixel-based inter prediction in coded texture assisted depth coding,

---

A divide-and-conquer hole-filling method for handling disocclusion in single-view rendering,

---

Fast reference frame selection based on content similarity for low complexity HEVC encoder,

---

Evaluation and modeling of depth feature incorporated visual attention for salient object segmentation,