This image features an academic poster presentation from the University of Amsterdam that delves into the topic of 3D generation and rendering using advanced generative models. The poster is authored by several individuals whose names, such as Zuoyue Li, Zhenqiang Li, and Zhaopeng Cui, are displayed prominently at the top. The left section of the poster explains the rationale behind 3D generation and highlights the superior consistency and flexibility it offers. It also emphasizes the advantages of using diffusion models over GANs, noting better performance and stability during training. The central portion of the poster focuses on a baseline comparison of methods and metrics using datasets such as HoliCity. This section contains various images showcasing the comparison results of different generative models, including methods like Sat2Vid, InfiniCity, and MVDiffusion. The bottom left part of the poster illustrates a process flowchart of how different components, such as point clouds and rendered images, interact within the generation model. Finally, the right section discusses model generalization with a focus on the OmniCity dataset, presenting images that showcase different perspectives like satellite view, ground view, and bird view for detailed analysis. Overall, the poster provides a comprehensive overview of innovative approaches to 3D generative modeling and their comparative performance, with ample visual data to support the findings. Text transcribed from the image: UNIVERSITY oft OF AMSTERDAM Zuoyue Li Zhenqiang Li Zhaopen en or predicted geometry and render sistency • Why 3D generation? Consistency naturally holds Do not need preset trajectory Why diffusion models instead of GANs? Better performance Stability during training 4 Experiment • Baseline comparison Method/Metric HoliCity dataset GT geometry Various metrics Sat2 Vid InfiniCity MVDiffusion Ours w/ different generative models 3D GAN-based method = 2D GAN-based method ion: 2D diffusion-model-based method Rendered Images B Generated background on Model Point cloud w/ feature M Sat. Ground-view Bird-view MVDiff. Ground-view Model generalization OmniCity data ture Factor Renderer Rendering Ours Bird-view