arXiv:2606. 29400v1 Announce Type: cross Abstract: In computer graphics, visual content is continuously warped, zoomed and resampled.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 09133v1 Announce Type: cross Abstract: Image super-resolution (SR) with large generative models has recently achieved remarkable perceptual quality, yet maintaining fidelity to the LR observation remains challenging.
Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos.
arXiv:2411. 17513v3 Announce Type: replace-cross Abstract: Modern deep-learning super-resolution (SR) techniques process images and videos independently of the underlying content and viewing conditions.
arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
arXiv:2606. 00746v1 Announce Type: cross Abstract: Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining.