6 papers
APEX: Asynchronous Prefix Denoising for Extreme Compression
David Dinkevich, Nisan Chiprut, Yoav HaCohen +1
Fewer latent tokens promise cheaper diffusion. Yet aggressive latent compression creates a reconstruction-generation dilemma: adding channels improves reconstruction but makes gene…
LiveSVG: Zero-Shot SVG Animation via Video Generation
Matan Levy, Ran Margolin, Bar Cavia +6
We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation methods struggle with comple…
Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization
Matan Levy, Gavriel Habib, Issar Tzachor +5
Template-free animatable head avatars can achieve high visual fidelity by learning expression-dependent facial deformation directly from a subject's capture, avoiding parametric fa…
CoatFusion: Controllable Material Coating in Images
Sagie Levy, Elad Aharoni, Matan Levy +2
We introduce Material Coating, a novel image editing task that simulates applying a thin material layer onto an object while preserving its underlying coarse and fine geometry. Mat…
Story2Board: A Training-Free Approach for Expressive Storyboard Generation
David Dinkevich, Matan Levy, Omri Avrahami +2
We present Story2Board, a training-free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key a…
Task-Specific Adaptation with Restricted Model Access
Matan Levy, Rami Ben-Ari, Dvir Samuel +2
The emergence of foundational models has greatly improved performance across various downstream tasks, with fine-tuning often yielding even better results. However, existing fine-t…