224 citations · 275 across the 10 of their papers we have counts for
7 papers · 1 filter
A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos
Xihua Sheng, Dong Liu, Chang Wen Chen
AI-generated videos are rapidly increasing in volume, duration, and resolution, creating growing demands for efficient storage and transmission. Unlike natural videos captured from…
Bi-Directional Deep Contextual Video Compression
Xihua Sheng, Li Li, Dong Liu +1
Deep video compression has made remarkable process in recent years, with the majority of advancements concentrated on P-frame coding. Although efforts to enhance B-frame coding are…
NVC-1B: A Large Neural Video Coding Model
Xihua Sheng, Chuanbo Tang, Li Li +2
The emerging large models have achieved notable progress in the fields of natural language processing and computer vision. However, large models for neural video coding are still u…
Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression
Xihua Sheng, Li Li, Dong Liu +1
Video compression performance is closely related to the accuracy of inter prediction. It tends to be difficult to obtain accurate inter prediction for the local video regions with…
Offline and Online Optical Flow Enhancement for Deep Video Compression
Chuanbo Tang, Xihua Sheng, Zhuoyuan Li +3
Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion in…
Attribute Artifacts Removal for Geometry-based Point Cloud Compression
Xihua Sheng, Li Li, Dong Liu +1
Geometry-based point cloud compression (G-PCC) can achieve remarkable compression efficiency for point clouds. However, it still leads to serious attribute compression artifacts, e…
Temporal Context Mining for Learned Video Compression
Xihua Sheng, Jiahao Li, Bin Li +3
We address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. For temporal context mining, we propose to store not only t…