Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models
arxiv(2023)
摘要
We address the problem of synthesizing multi-view optical illusions: images
that change appearance upon a transformation, such as a flip or rotation. We
propose a simple, zero-shot method for obtaining these illusions from
off-the-shelf text-to-image diffusion models. During the reverse diffusion
process, we estimate the noise from different views of a noisy image, and then
combine these noise estimates together and denoise the image. A theoretical
analysis suggests that this method works precisely for views that can be
written as orthogonal transformations, of which permutations are a subset. This
leads to the idea of a visual anagram–an image that changes appearance under
some rearrangement of pixels. This includes rotations and flips, but also more
exotic pixel permutations such as a jigsaw rearrangement. Our approach also
naturally extends to illusions with more than two views. We provide both
qualitative and quantitative results demonstrating the effectiveness and
flexibility of our method. Please see our project webpage for additional
visualizations and results: https://dangeng.github.io/visual_anagrams/
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要