arXiv:2512.14234v2 Announce Type: replace
Abstract: Human communication is inherently multimodal and social: words, prosody, and body language jointly carry intent. Yet most prior systems model human behavior as a translation task co-speech gesture or…
arXiv:2604.13863v1 Announce Type: new
Abstract: Image generation technology can synthesize condition-specific images to supplement real-world industrial anomaly data and enhance anomaly detection model performance. Existing generation techniques rarel…
arXiv:2602.16385v4 Announce Type: replace
Abstract: Independent indoor mobility remains a critical challenge for individuals with visual impairments, largely due to the limited capability of existing assistive systems in detecting fine-grained hazardo…
arXiv:2602.20981v3 Announce Type: replace-cross
Abstract: Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and frame-level video information. In this work,…
arXiv:2604.13918v1 Announce Type: new
Abstract: We present PartNerFace, a part-based neural radiance fields approach, for reconstructing animatable facial avatar from monocular RGB videos. Existing solutions either simply condition the implicit networ…
arXiv:2603.08639v2 Announce Type: replace-cross
Abstract: Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as…
arXiv:2604.07823v2 Announce Type: replace-cross
Abstract: Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Learning such performance from video is a pro…
arXiv:2604.10532v2 Announce Type: replace
Abstract: This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural an…
arXiv:2604.14025v1 Announce Type: cross
Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditi…
arXiv:2604.12525v2 Announce Type: replace
Abstract: Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compression scenarios th…