5 papers
Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation
Zhenjie Liu, Binyan Chen, Hao Chen +2
Identity-preserving text-to-video generation aims to synthesize a video that accurately follows a textual description while maintaining the recognizability of a user-specified subj…
DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
Renjie Lu, Xulong Zhang, Xiaoyang Qu +2
Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lie…
MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control
Renjie Lu, Xulong Zhang, Xiaoyang Qu +2
Synthesizing personalized talking faces that uphold and highlight a speaker's unique style while maintaining lip-sync accuracy remains a significant challenge. A primary limitation…
ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search
Zhenjie Liu, Jianzhang Lu, Renjie Lu +2
Recent advancements in video diffusion models have significantly enhanced audio-driven portrait animation. However, current methods still suffer from flickering, identity drift, an…
NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results
Xiaohong Liu, Xiongkuo Min, Qiang Hu +92
This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) a…