12 papers
VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
Huilin Deng, Hongchen Luo, Wei Zhai +2
Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, de…
Gloria: Consistent Character Video Generation via Content Anchors
Yuhang Yang, Fan Zhang, Huaijin Pi +5
Digital characters are central to modern media, yet generating character videos with long-duration, consistent multi-view appearance and expressive identity remains challenging. Ex…
MatE: Material Extraction from Single-Image via Geometric Prior
Zeyu Zhang, Wei Zhai, Jian Yang +1
The creation of high-fidelity, physically-based rendering (PBR) materials remains a bottleneck in many graphics pipelines, typically requiring specialized equipment and expert-driv…
Event Stream Filtering via Probability Flux Estimation
Jinze Chen, Wei Zhai, Yang Cao +2
Event cameras asynchronously capture brightness changes with microsecond latency, offering exceptional temporal precision but suffering from severe noise and signal inconsistencies…
MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking
Han Han, Wei Zhai, Yang Cao +2
Tracking Any Point (TAP) plays a crucial role in motion analysis. Video-based approaches rely on iterative local matching for tracking, but they assume linear motion during the bli…
MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling
Jian Yang, Dacheng Yin, Yizhou Zhou +4
Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, w…