把真实房间搬进模拟器，AI 终于能逐个摆弄家具了
过去让 AI 把真实房间变成可编辑的 3D 模型，每一步都要求完美输入：物体不能遮挡、视角要全、模型得精准——现实里根本做不到。Lucida 把要求拆开，让每一步只吃真实拍摄能提供的东西：先解析视频成场景图，每个物体带多视角证据；再为每个物体生成完整资产；最后用视觉语言模型像人拖拽 3D 手柄一样，反复微调位置直到对齐。结果：物体检测精度提升 69%，姿态估计成功率从 57.8% 涨到 83.4%，场景重建分数从 0.794 升到 0.924。这不是你明天能用的工具，但它意味着机器人训练和 AR 应用离『扫描一下房间就能模拟』更近了一步。
📄 原文摘要(英文)
Composable scene modeling aims to recover a real indoor scene as complete, editable object assets arranged as observed, giving robot simulation and embodied AI a simulation-ready replica of the real environment whose objects can be manipulated individually. Existing pipelines decompose the task into three steps---parse the observations into instances, generate an asset for each, and place each asset back---but every step presumes an input that a cluttered capture rarely provides: accurate instance geometry, unoccluded views, and assets that accurately match the observations. We propose Lucida, which keeps this order but redistributes the requirements, so each step consumes only what a real capture reliably provides and precision is reached at the end of the pipeline rather than demanded at its start. Lucida parses the video into a scene graph whose nodes carry per-instance multi-view evidence, generates a complete asset for each instance from its evidence, and places assets with GizmoAct, a VLM policy that casts placement as multi-turn GUI interaction, manipulating the object's gizmo in a closed loop and deciding itself when alignment is reached. Across scene-level 3D object detection, object pose estimation, and scene reconstruction, Lucida improves mAP over Boxer by 69% on R2S-Scene, raises [email protected] from 57.8% to 83.4% on CA-1M, and increases scene F-Score from 0.794 for SAM3D to 0.924.