# 在Blender中思考：基于视觉语言模型的可执行分阶段逆向图形

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-01 08:00
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmpw5g4y2007hsl1ul5dcg2lr
- 原文链接：https://arxiv.org/abs/2606.02580

## AI 摘要

本研究探讨预训练视觉语言模型能否通过生成可执行的Blender程序，直接从单张图像重建为可编辑的3D场景，且不依赖专门的2D/3D基础模型、可微渲染或多视图监督。文章提出了“可执行分阶段逆向图形”（SEIG）智能体框架，该框架在可执行的Blender代码空间中，通过分阶段优化几何、材质、构图与光照等因子来重建场景。实验评估表明，分阶段重建策略显著提升了场景重建的保真度（包括像素级、感知和语义保真度），验证了任务分解对于通用视觉语言模型执行可执行逆向图形的重要性。重建后的可编辑Blender场景可支持多种下游应用。

## 正文

Inverse graphics is a longstanding and highly underconstrained problem that seeks to reconstruct images as editable 3D scenes which can be rendered, relit, and manipulated. In this work, we investigate whether pretrained vision-language models (VLMs) can perform executable inverse graphics directly from a single image by reconstructing a scene as an editable Blender program, without relying on specialized 2D or 3D foundation models, differentiable rendering, or multi-view supervision. We introduce Staged Executable Inverse Graphics (SEIG), an agentic framework that reconstructs a 3D scene from a single image by progressively refining scene factors including geometry, materials, composition, and lighting directly in executable Blender code space. We evaluate our framework across diverse scenes using a range of reconstruction metrics spanning pixel-level, perceptual, and semantic fidelity. Our experiments show that staged reconstruction substantially improves reconstruction fidelity, highlighting the importance of task decomposition for executable inverse graphics with general-purpose VLMs. Finally, we showcase various downstream applications enabled by the reconstructed editable Blender scenes.