SOURCE-LINKED INTELLIGENCE

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

We present FlashRender, a few-step generative rendering framework that retakes a source video along a target camera trajectory in seconds. We identify sampling-step-dependent camera control as a prominent manifestation of discretization error in existing multi-step generative rendering models and show that resolving this inconsistency substantially lowers denoising trajectory curvature, facilitating subsequent step distillation. To this end, we introduce Representation Transformation and Alignment (RETA), which aligns hidden source-video representations with target-video features from a frozen

Read original source ↗ Open in workspace

recordType

paper

region

Global