Despite yielding higher visual quality than image-to-image approaches, masked generation paradigms for video face editing fundamentally lack attribute consistency (e.g., illumination, background). We introduce LumaID, a novel framework that explicitly disentangles identity and expression representations from environmen...
Yi-Ying Wei, Xuanhong Chen, Hadi Amirpour et al.· Proceedings of the 34th ACM...· 0 citations
The growing integration of vision and language models is driving a fundamental shift in video understanding and processing. This evolution calls for datasets that jointly capture visual content and its semantic representations at scale. To address this need, we introduce LMM-10K, a large-scale curated multimodal datase...
Mohammad Ghasempour, Yi-Ying Wei, Hadi Amirpour et al.· Proceedings of the 34th ACM...· 1 citation
Quantitative evidence is provided that modern passthrough augmented reality systems can support reliable controller-free precision interaction, while also clarifying how depth and cognitive demand shape user performance and experience.
Milad Ghanbari, Yu-Jie Huang, Wei Zhou et al.· Proceedings of the 4th Inter...· 0 citations
Attention-Scoped Guidance (ASG), a sampler wrapper that reads a soft support map from the instruction attention that the editor already computes, then weakens text guidance where support is low and strengthens image anchoring where support is high.
Zeyan Li, Wei Zhou, Hadi Amirpour et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.