activity
20242026
collaborators

6 papers

cs.CV2026

FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows

Daniel Gilo, Sven Elflein, Ido Sobol +1

Conditional diffusion and flow models routinely fail to satisfy the very constraints that define their task. For instance, a depth-conditioned model often produces images whose re-…

cs.GR2026

Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning

Ido Sobol, Kihyuk Sohn, Yoav Blum +4

We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-…

cs.CV2026

RealMaster: Lifting Rendered Scenes into Photorealistic Video

Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun +5

State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Fu…

cs.CV2025

Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis

Saar Stern, Ido Sobol, Or Litany

The goal of Novel View Synthesis (NVS) is to generate realistic images of a given content from unseen viewpoints. But how can we trust that a generated image truly reflects the int…

cs.CV2025

A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision

Chensheng Peng, Ido Sobol, Masayoshi Tomizuka +3

We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the…

cs.CV2024

Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering

Ido Sobol, Chenfeng Xu, Or Litany

Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce…