arXiv subjects

Zohar Barzelay

Publications and source records attributed to Zohar Barzelay.

3 recordsLinked to original sources

arXiv2026

Photorealistic Novel View Synthesis of Human Faces using Next-Scale Transformers

Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving identity, fine appearance details, and geometric coherence is critical. We build on the next-scale autoregressive paradigm and adapt it for human-centric view synthesis by enabling higher image resolutions, multi-view outputs and stronger cross-view consistency in a single forward pass. We train on a synthetic dataset of human faces spanning diverse identities and apparel. Contrary to diffusion models, this paradigm does not need 2D pre-training and, thanks to its next-scale architecture, it benefits from lower-resolution, general-purpose pre-trainings, with the full-sized purpose-specific images being used only in the last training stages. This enables our architecture to converge with a smaller amount of purpose-specific training data, allowing us to use a smaller but more realistic training dataset. The resulting model produces sharp and realistic views, with the option to synthesize multiple novel viewpoints simultaneously for improved agreement across views. Empirically, we observe gains in perceptual fidelity and cross-view coherence on human subjects, demonstrating that next-scale autoregression is an effective backbone for scalable, multi-output human view synthesis. We also couple our pipeline with an existing transformer-based model for pixel-aligned 3D gaussian lifting from multi-view facial inputs, resulting in accurate and photorealistic 3D models of human faces.

cs.CV↗

arXiv2025

Capture, Canonicalize, Splat: Zero-Shot 3D Gaussian Avatars from Unstructured Phone Images

We present a novel, zero-shot pipeline for creating hyperrealistic, identity-preserving 3D avatars from a few unstructured phone images. Existing methods face several challenges: single-view approaches suffer from geometric inconsistencies and hallucinations, degrading identity preservation, while models trained on synthetic data fail to capture high-frequency details like skin wrinkles and fine hair, limiting realism. Our method introduces two key contributions: (1) a generative canonicalization module that processes multiple unstructured views into a standardized, consistent representation, and (2) a transformer-based model trained on a new, large-scale dataset of high-fidelity Gaussian splatting avatars derived from dome captures of real people. This "Capture, Canonicalize, Splat" pipeline produces static quarter-body avatars with compelling realism and robust identity preservation from unstructured photos.

cs.CV↗

arXiv2023

PhysGraph: Physics-Based Integration Using Graph Neural Networks

Physics-based simulation of mesh based domains remains a challenging task. State-of-the-art techniques can produce realistic results but require expert knowledge. A major bottleneck in many approaches is the step of integrating a potential energy in order to compute velocities or displacements. Recently, learning based method for physics-based simulation have sparked interest with graph based approaches being a promising research direction. One of the challenges for these methods is to generate models that are mesh independent and generalize to different material properties. Moreover, the model should also be able to react to unforeseen external forces like ubiquitous collisions. Our contribution is based on a simple observation: evaluating forces is computationally relatively cheap for traditional simulation methods and can be computed in parallel in contrast to their integration. If we learn how a system reacts to forces in general, irrespective of their origin, we can learn an integrator that can predict state changes due to the total forces with high generalization power. We effectively factor out the physical model behind resulting forces by relying on an opaque force module. We demonstrate that this idea leads to a learnable module that can be trained on basic internal forces of small mesh patches and generalizes to different mesh typologies, resolutions, material parameters and unseen forces like collisions at inference time. Our proposed paradigm is general and can be used to model a variety of physical phenomena. We focus our exposition on the detail enhancement of coarse clothing geometry which has many applications including computer games, virtual reality and virtual try-on.

cs.GR↗