From the 6 of 173 papers with an AI index.
79 citations
- University of ChicagoUS39 papers
- University of MichiganUS36 papers
- University of OxfordGB34 papers
- University of California SystemUS33 papers
- Queen Mary University of LondonGB31 papers
- University of CambridgeGB31 papers
- Yale UniversityUS31 papers
- Stony Brook UniversityUS30 papers
- University of GenevaCH30 papers
- Lawrence Berkeley National LaboratoryUS29 papers
- Michigan State UniversityUS29 papers
- University of EdinburghGB29 papers
6 papers · 1 filter
Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction
Yufan Zhang, Yu Ji, Ayo Ajiboye +4
We present a diffusion-based method for relighting dynamic portrait videos with photorealism and temporal consistency. Our method is fueled by a hybrid training dataset that consis…
Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?
Xuezheng Chen, Zhengbo Zou
Construction safety inspections typically involve a human inspector identifying safety concerns on-site. With the rise of powerful Vision Language Models (VLMs), researchers are ex…
Forecasting Solar Energy Using a Single Image
Jeremy Klotz, Shree K. Nayar
Solar panels are increasingly deployed in cities on rooftops, walls, and urban infrastructure. Although the panel costs have fallen in recent years, the soft costs of installing th…
Do vision models perceive illusory motion in static images like humans?
Isabella Elaine Rosario, Fan L. Cheng, Zitang Sun +1
Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in…
Margin-Consistent Deep Subtyping of Invasive Lung Adenocarcinoma via Perturbation Fidelity in Whole-Slide Image Analysis
Meghdad Sabouri Rad, Junze, Huang +6
Whole-slide image classification for invasive lung adenocarcinoma subtyping remains vulnerable to real-world imaging perturbations that undermine model reliability at the decision…
Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
Runzhou Liu, Hailey Weingord, Sejal Mittal +18
Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important…