all AI news
Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models
April 4, 2024, 4:45 a.m. | Daniel Geng, Inbum Park, Andrew Owens
cs.CV updates on arXiv.org arxiv.org
Abstract: 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 …
arxiv cs.cv diffusion diffusion models optical type view visual
More from arxiv.org / cs.CV updates on arXiv.org
Retrieval-Augmented Egocentric Video Captioning
2 days, 14 hours ago |
arxiv.org
Mirror-Aware Neural Humans
2 days, 14 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US