arXiv:2503.04500v3 Announce Type: replace-cross Abstract: Video understanding has largely relied on deep spatiotemporal architectures, including 3D convolutional networks and optical flow (OF) based models. While effective, these methods are often computationally expensive and de…
arXiv cs.LG
TIER_1English(EN)·Sidi Mohamed Sid'El Moctar, Nicolas Vitry, H\'el\`ene Bouvrais·
arXiv:2608.19965v1 Announce Type: cross Abstract: Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large variations in structure morphology. While deep learning approache…
arXiv:2608.18004v1 Announce Type: new Abstract: Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-based models (EBMs) are a natural fit since energies compose additively, which ena…
Energy-Guided Flow Matching improves generative quality by progressively revealing high-frequency details through a moving endpoint and adaptive scheduling, reducing training cost and achieving state-of-the-art FID scores.
arXiv:2608.20112v1 Announce Type: cross Abstract: Generative models have shown strong potential for positron emission tomography (PET) image reconstruction. Although diffusion model-based reconstruction methods have demonstrated promising performance, they often require many reve…
arXiv:2502.16445v4 Announce Type: replace-cross Abstract: Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems. Nonetheless, training a generator is a no…
arXiv:2602.01115v3 Announce Type: replace-cross Abstract: Diffusion-based visuomotor policies excel at modeling action distributions but are inference-inefficient, since recursively denoising from noise to policy requires many steps and heavy UNet backbones, which hinders deploym…
arXiv:2608.17695v1 Announce Type: new Abstract: Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact, the original model is not necessary for all denoising steps, allowing some ste…
arXiv cs.CV
TIER_1English(EN)·Arman Zarei, Mahdi M. Kalayeh·
arXiv:2608.15452v1 Announce Type: new Abstract: Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images, yet this source distribution carries no notion of spatial structure. Images however are fundamentally l…
