# 面向问题引导主动视觉的免渲染前瞻

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-11039
> 频道：papers | 更新日期：2026-10-08 | 标签：arxiv, cs.RO
> 核心摘要：针对依赖视角的问答相机运动选择，RFL用离线特权视觉前瞻蒸馏免渲染策略，并在E3VS-Bench未见环境中验证。

# 面向问题引导主动视觉的免渲染前瞻

::: v-pre
> 原文链接：[Rendering-Free Lookahead for Question-Guided Active Vision](https://arxiv.org/abs/2610.11039)（arXiv 2610.11039 · 发布日期：2026-10-08）

**Rendering-Free Lookahead for Question-Guided Active Vision**

针对依赖视角的问答相机运动选择，RFL用离线特权视觉前瞻蒸馏免渲染策略，并在E3VS-Bench未见环境中验证。

## 核心要点

- 问题在于当前视角可能遮挡关键信息，需要选择能暴露证据的相机运动。
- RFL以VLM估计的answerability衡量候选未来视角对回答问题的有用性。
- 训练时教师在3DGS场景渲染未来视图，用冻结VLM生成一步和两步目标并蒸馏学生。
- 部署时不渲染未来视图；377个E3VS-Bench回合中均值评分较基线提升43%。

**验证范围与局限**：验证范围为未见环境中的377个E3VS-Bench测试回合。

## 英文摘要 (Abstract)

Active robot vision requires controlling the camera to reveal task-relevant information that is hidden from the current viewpoint. For example, determining what is inside a box may require raising the camera and looking down into it. For viewpoint-dependent question answering, the challenge is to select camera motions that expose the visual evidence needed to answer the question. Although vision-language models (VLMs) can interpret observed images, selecting such motions requires anticipating the usefulness of unseen views. We quantify this usefulness as answerability, a VLM's estimate that a view suffices to answer the question, and present Rendering-Free Lookahead (RFL), a viewpoint-selection policy that ranks candidate camera motions by predicted future answerability. RFL transfers visual lookahead from deployment to offline training. At training, a privileged teacher renders candidate future views in 3D Gaussian Splatting (3DGS) scenes and uses a frozen VLM to compute one- and two-step answerability targets. Through two-stage distillation, a student learns to predict these action values from the question, recent visual observations, and a candidate camera motion. At deployment, RFL uses these predicted values to select camera motions without rendering future views. On 377 E3VS-Bench test episodes in unseen environments, RFL improves the mean judge score by 43\% over a direct-action baseline using the same VLM. These results support learning camera-control policies from privileged visual lookahead for viewpoint-dependent question answering.

作者：Koya Sakamoto, Daichi Azuma, Shuhei Kurita, Naoya Chiba, Yusuke Iwasawa, Yutaka Matsuo, Taiki Miyanishi
:::

## 原始参考来源 (Sources)

- [arXiv 2610.11039：Rendering-Free Lookahead for Question-Guided Active Vision](https://arxiv.org/abs/2610.11039)