40 citations · 102 across the 11 of their papers we have counts for
7 papers · 1 filter
Auto-Regressive Models Need Structural Registers: Semantic Foresight Improves Coherent Driving Video Continuation
Ruibo Ming, Jingwei Wu, Zhewei Huang +5
Front-view driving video continuation is a critical component for constructing sophisticated world models. However, maintaining long-term coherence faces the fundamental challenge…
A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches
Ruibo Ming, Zhewei Huang, Jingwei Wu +5
Future Frame Synthesis (FFS), the task of generating subsequent video frames from context, represents a core challenge in machine intelligence and a cornerstone for developing pred…
Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
Zhewei Huang, Ailin Huang, Xiaotao Hu +3
The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolu…
A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
Xiaotao Hu, Zhewei Huang, Ailin Huang +2
The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra…
Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer
Ailin Huang, Zhewei Huang, Shuchang Zhou
This paper reports our solution for ACM Multimedia ViCo 2022 Conversational Head Generation Challenge, which aims to generate vivid face-to-face conversation videos based on audio…
Real-Time Intermediate Flow Estimation for Video Frame Interpolation
Zhewei Huang, Tianyuan Zhang, Wen Heng +2
Real-time video frame interpolation (VFI) is very useful in video processing, media players, and display devices. We propose RIFE, a Real-time Intermediate Flow Estimation algorith…
Learning to Paint With Model-based Deep Reinforcement Learning
Zhewei Huang, Wen Heng, Shuchang Zhou
We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings. By employing a neural renderer in model-based Deep…