# FlashRender：基于相机控制视频 MeanFlow 的少步生成渲染框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-03 08:00
- AIHOT 分数：39
- AIHOT 链接：https://aihot.virxact.com/items/cmtmeb7fn00x9rotxrofjkgoc
- 原文链接：https://arxiv.org/abs/2609.03563

## AI 摘要

论文提出 FlashRender，一个少步生成渲染框架，可在数秒内沿目标相机轨迹重新渲染源视频。方法引入 RETA 将源视频隐表示与冻结视觉几何模型的目标视频特征对齐，实现采样步数一致的相机控制，再用 MeanFlow 目标微调并结合 on-policy flow map 蒸馏。实验显示其在视频质量和几何一致性上匹配多步基线，采样成本降低 25 倍，并在分布外目标相机轨迹下具备更强的相机可控性。

## 正文

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 visual geometry model. This directly encodes the geometric transformation within the source-video stream, enabling sampling-step-consistent camera control. We then fine-tune the model with the MeanFlow objective on the lower-curvature denoising trajectory induced by RETA, allowing the model to more effectively address discretization error. Finally, we apply on-policy flow map distillation to correct self-rollout errors under fixed few-step sampling. Extensive experiments show that RETA, MeanFlow, and on-policy flow map distillation play complementary roles in few-step generative rendering. Together, they enable our approach to match multi-step baselines in video quality and geometric consistency at 25x lower sampling cost while achieving superior camera controllability, even under out-of-distribution target camera trajectories.