1 code implementation • 29 Nov 2023 • Haoran Ma, Yan Zhang, Pengyuan Liu, Fan Zhang, Pengyu Zhu
In this work, a spatial-dependent graph neural networks (GNNs) approach is proposed to reveal the relation between spatial structure and restoration quality on an urban scale.
no code implementations • 29 Nov 2023 • Haoran Ma, Dongdong Wu
However, this approach using only image-shallow information makes it difficult to comprehensively understand the deep semantic features of human perception of a scene.
no code implementations • 23 Feb 2023 • Haoran Ma
We first fine-tuned the Stable Diffusion model on the CMP Fa-cades dataset using the LoRA (Low-Rank Adaptation) approach, then we ap-ply the ControlNet model to further control the output.
1 code implementation • 8 Mar 2020 • Haoran Ma, Benyamin Ghojogh, Maria N. Samad, Dongyu Zheng, Mark Crowley
We propose a new method, named isolation Mondrian forest (iMondrian forest), for batch and online anomaly detection.