Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

H Du, S Zhang, B **e, G Nan, J Zhang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Video anomaly understanding (VAU) aims to automatically comprehend unusual
occurrences in videos thereby enabling various applications such as traffic surveillance and …

Real-time 3D-aware portrait video relighting

Z Cai, K Jiang, SY Chen, YK Lai… - Proceedings of the …, 2024 - openaccess.thecvf.com
Synthesizing realistic videos of talking faces under custom lighting conditions and viewing
angles benefits various downstream applications like video conferencing. However most …

Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly

H Du, G Nan, J Qian, W Wu, W Deng, H Mu… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advancements in video anomaly understanding (VAU) have opened the door to
groundbreaking applications in various fields, such as traffic monitoring and industrial …

Deep Learning-based Light Source Estimation from Face Images

P Hochhauser - 2024 - repositum.tuwien.at
This thesis proposes a novel method to estimate realistic-looking environment images from
an input face image. Having correct light information is crucial for a variety of virtual and …

Inclusive Portrait Lighting Estimation Model Leveraging Graphic-Based Synthetic Data

KCL Chau, LI Tao, R Jiang, Z Yu, PA Bokaris - Synthetic Data for Computer … - openreview.net
We propose a synthetic data-based training framework for real-time deep learning models
that predict an omnidirectional high-dynamic-range (HDR) environment light map from a …