Ariel Shamir

Material Coating is a novel image editing task that simulates applying a thin material layer to a target surface (substrate) while preserving the substrate's geometry and shading. Material coating is fundamentally different from material transfer, which typically reinterprets an object as being made of a new material and can modify its shape or overwrite fine details. We introduce CoatFusion , a diffusion-based framework for controllable material coating in images. Since real paired before/after coating data is difficult to acquire, we construct DataCoat110K , a synthetic paired dataset of approximately 110K examples rendered with physically motivated coating layers, including opaque, metallic, and transmissive appearances. CoatFusion formulates coating as visual in-context learning over a triptych containing the substrate image, a canonical 2D albedo texture, and the coated result, and uses cycle-consistent compose/decompose supervision to encourage substrate preservation and geometry-aware texture wrapping. Learned material tokens provide continuous control over roughness and thickness, and discrete on/off control over metalness and transmission. Across held-out synthetic evaluations, real-image examples, ablations, and a human study, CoatFusion produces more realistic and controllable coatings than material transfer/editing baselines and classical blending operations. Code and data for this paper are available at https://github.com/sagielevy/coatFusion.

Faithfully capturing diverse real-world objects with fuzzy, anisotropic structures—such as hair, fur, fibers, and textiles—for efficient real-time visualization remains challenging. Recent radiance field reconstruction methods capture these structures from multi-view images using translucent volumetric primitives such as 3D Gaussians rather than opaque low-dimensional primitives (e.g., triangles, line segments, and polylines), thereby limiting compatibility with standard depth-tested rasterization, reflection modeling, and physical simulation. We present an inverse rendering method for reconstructing fuzzy geometry using explicit line segments, which are rasterized on a subpixel grid for anti-aliasing to reproduce a semi-transparent appearance. While straightforward to render, optimizing numerous line primitives to match target images poses a significant challenge. We address this by introducing a stochastic differentiable rasterizer for line segments that produces informative gradients with respect to vertex positions, attributes, and discrete connectivity. Experiments on synthetic and real-world datasets show that our method outperforms surface-based approaches in capturing fuzzy boundaries and achieves quality comparable to volumetric representations while relying entirely on explicit geometry. The resulting representation integrates seamlessly with standard graphics pipelines, enabling cross-platform rendering, various shading models, and physical simulation.

While recent advances in co‐speech gesture generation have achieved impressive rhythmic synchronization, synthesizing gestures that are both semantically meaningful and faithful to a speaker's unique non‐verbal style remains an open challenge. Semantic gestures, such as iconic shapes or deictic pointing, are statistically sparse, making them difficult to learn effectively within standard generative models. We present SiGnature, a framework for Stylized and Semantic Gesture generation that reconciles precise semantic control with high‐fidelity style preservation. Unlike prevalent methods that rely on entangled latent representations, SiGnature operates in an explicit joint‐rotation space. This design enables our core contribution, Joint Motion Integration (JMI), a training‐free inference mechanism capable of injecting any external motion sequence, particularly in‐the‐wild semantic gestures, directly into the diffusion process. JMI automatically identifies the specific “active joints” conveying a semantic action and injects them into the generation, while relying on the diffusion backbone to synthesize the remaining body dynamics, including posture and flow, in accordance with the pre‐learned style of the target speaker. This allows for the plug‐and‐play integration of arbitrary motions, including complex semantic gestures, without retraining or introducing the “Frankenstein” artifacts typical of cut‐and‐paste methods. Extensive experiments and perceptual studies demonstrate that SiGnature offers superior semantic motion control while maintaining smooth and natural co‐speech gesture generation and preserving the distinct characteristics of the speaker, thereby outperforming state‐of‐the‐art baselines.

Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its absence of structure. However, this very property limits control over, and predictability of, specific visual attributes, as the noise is not human-interpretable. In this work, we investigate the characteristics of the input noise in diffusion models. We show that, although all frequencies in white Gaussian noise have comparable statistical energy, low-frequency components primarily determine the image’s global structure and color composition, while high-frequency components control finer details. Building on this observation, we demonstrate that simple manipulations of the low-frequency noise using low-frequency image priors can effectively condition the generation process to reconstruct these low-frequency visual cues. This allows us to define a simple, training-free method with minimal overhead that steers overall image structure and color, while letting high-frequency components freely emerge as fine details, enabling variability across generated outputs.

In this work we extend speaker‐centric audio‐driven gesture synthesis toward a unified conversational model that jointly captures both speaking and listening behaviors. Existing speaker‐centric models effectively generate gestures aligned with speech but overlook the bidirectional dynamics that characterize natural dialogue. To address this limitation, we propose the Conversational Gesture Model (CGM), a cross‐attention‐based model capable of synthesizing gestures conditioned on interlocutor conversational cues such as gestures, tone, and textual semantics. By leveraging cross‐attention mechanisms, the model fuses interlocutor audio and text features with character gesture encodings, enabling a single system to seamlessly alternate between speaking and listening roles of the same character. Hence, our model enables a single system to act as both speaker and listener, capturing the fluid role shifts and mutual influence inherent in conversation. Experiments demonstrate that this approach preserves the quality of speaker‐driven gestures while significantly improving the realism, coherence, and responsiveness of full conversational interactions.

Despite widespread use, charts remain largely inaccessible for Low-Vision Individuals (LVI). Reading charts requires viewing data points within a global context, which is difficult for LVI who may rely on magnification or experience a partial field of vision. We aim to improve exploration by providing visual access to critical context. To inform this, we conducted a formative study with five LVI. We identified four fundamental contextual elements common across chart types: axes, legend, grid lines, and the overview. We propose two pointer-based interaction methods to provide this context: Dynamic Context, a novel focus+context interaction, and Mini-map, which adapts overview+detail principles for LVI. In a study with N=22 LVI, we compared both methods and evaluated their integration to current tools. Our results show that Dynamic Context had significant positive impact on access, usability, and effort reduction; however, worsened visual load. Mini-map strengthened spatial understanding, but was less preferred for this task. We offer design insights to guide the development of future systems that support LVI with visual context while balancing visual load.

Translation gain is a key Redirected Walking (RDW) technique in Virtual Reality (VR) that enables users to navigate virtual environments (VEs) larger than the available physical space. The technique was originally developed to scale users' walking distance in the VE and is typically applied continuously, regardless of the user's motion state. We introduce Gait-Synced Translation Gain (GSTG), a novel approach that adapts translation gain by synchronizing it with the user's gait cycle. GSTG leverages the single-limb support phase of walking-when users are less stable and thus less sensitive to external disturbances-to apply higher levels of gain. This approach allows greater manipulation while preserving natural walking sensations and avoiding additional cybersickness. A user study comparing GSTG with continuous translation gain demonstrates significant improvements in perceived naturalness and comfort. Our results highlight the potential of gait-synchronized gain to enhance immersion, offering new possibilities for more realistic and comfortable VR locomotion.