3 papers
cs.CV2026
Reviving ConvNeXt for Efficient Convolutional Diffusion Models
Taesung Kwon, Lorenzo Bianchi, Lennart Wittke +5
Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter effic…
cs.CV2025
LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping
Pascal Chang, Sergio Sancho, Jingwei Tang +2
Anamorphosis refers to a category of images that are intentionally distorted, making them unrecognizable when viewed directly. Their true form only reveals itself when seen from a…
cs.CV2025
How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models
Pascal Chang, Jingwei Tang, Markus Gross +1
Video editing and generation methods often rely on pre-trained image-based diffusion models. During the diffusion process, however, the reliance on rudimentary noise sampling techn…