This work proposes a novel training-sampling approach for single-image multi-scale diffusion models that enables consistent and joint sampling of image sequences and introduces a Laplacian-recomposition sampling algorithm to enforce multi-scale consistency.
Observation Operator Diffusion is proposed, a unified framework that aligns both the supervision trajectory and feature refinement with the intrinsic recovery order of image structures and introduces GL-CoDA, a decoder that injects scale-specific Gaussian-Lanczos observations across decoding stages for coarse-to-fine f...
Shaojie Guo, Li-Chen Ma, Haoyang Tong et al.· 1 citation
Qualitative results reveal superior reconstructions and interpretable decompositions compared to classical decomposition, joint alignment, and 3D object modeling methods, while maintaining a simple 2D formulation, suggesting that meaningful object discovery can emerge from single image learning alone.
Syrine Kalleli, Alexei A. Efros, Mathieu Aubry· 0 citations
This work repurposes pretrained video generative models as a unified and data-efficient framework for geometry estimation, formulated innovatively as a next-frames prediction task, and inherits naturally structured knowledge and richer priors from the video model, enabling more data efficient and effective learning of...
Haosen Yang, Ji-Fei Song, Zhensong Zhang et al.· 1 citation
This work proposes a perceptually regularized diffusion framework that incorporates prior knowledge through perceptual-loss-based regularization, improving training convergence and encouraging the recovery of meaningful image features.
Chuxiang Wang, Pavithra Venkatachalapathy, Ying Liang et al.· 0 citations
PixRestore is presented, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining.
Ling-Chen Sun, Rong-Yuan Wu, Xiang-Tao Kong et al.· 2 citations
Blind image deconvolution, the task of recovering a sharp image from a blurred observation with an unknown kernel, remains a challenging ill-posed inverse problem. While deep learning methods trained on large-scale datasets have achieved remarkable performance, their application is often limited by the availability of...
Ting-Ting Wu, Pei-Xuan Song, Wu-Fan Zhao et al.· IEEE Transactions on Computa...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
