发表机构
Studio π（Studio π）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PACE提出一种类型化规范，将剧本转化为精确的摄像机与场景布局，通过编译器生成提示词和3D场景，并逐字段测量几何一致性，实验表明其能显著提升动作绘制准确率。
AI 中文摘要
在剧本与电影之间，存在一个以空间为首要的规划问题：谁站在哪里，以及摄像机从其所处位置能看到什么。当以自由文本形式向图像扩散模型请求一个镜头时，该模型会依据其自身默认设置来解决这一规划问题。我们提出PACE（精确AI电影化表达），一种用于该规划的类型化表示：剧本依据、所需的角色、道具和地点、每个主体所站的位置，以及摄像机的动作。一个值在其所属层级（剧本、场景、镜头或分镜）被写入一次，并向下继承。一个编译器将结果转化为发送给扩散模型的提示词，以及一个以米为单位构建的3D场景；一个摄像机求解器放置摄像机，使得所声明的取景即为所构建的取景。当声明的值成为几何时，PACE逐字段地测量编译后的摄像机与舞台化渲染结果偏离声明的程度，而非要求模型进行判断。在包含11个场景的Automatic Drive剧本上，每个单主体的舞台化分镜将其主体放置在距其声明位置不超过帧宽1.2%的范围内；当有两个或三个主体时，单一的摄像机姿态无法满足所有位置，此时会报告残差而非将其吸收。在204个外部导演-故事板镜头中，从导演文字得到的交付头部高度是舞台化目标的1.906倍，从编译提示词得到的是1.733倍，而使用灰盒控制则为0.955倍；最能保持取景的条件所绘制的动作最少。在30个镜头上声明姿态，将所绘制的动作从58.9%提升至74.4%，且不改变取景。转场、拟合运动以及人工审查生成的画面仍是待办事项。代码：此HTTPS链接
英文摘要
Between a screenplay and a film sits a planning problem that is spatial first: who stands where, and what a camera sees from where it stands. An image diffusion model asked for a shot in free text settles that plan by its own defaults. We present PACE (Precise AI Cinematic Expression), a typed representation for the plan: the screenplay evidence, the characters, props and locations it needs, where each subject stands, and what the camera does. A value is written once at the level it belongs to (script, scene, shot or panel) and inherited below it. A compiler turns the result into both the prompt sent to the diffusion model and a 3D scene built in metres, and a camera solver places the camera so that the declared framing is the framing built. Where a declared value becomes geometry, PACE measures, field by field, how far the compiled camera and the staged render sit from the declaration, rather than asking a model to judge. On the 11-scene Automatic Drive screenplay, every staged single-subject panel places its subject within 1.2% of frame width of its declared position; with two or three subjects one camera pose cannot satisfy every position, and the residual is reported rather than absorbed. On 204 external director-storyboard shots, delivered head height is 1.906 times the staged target from the director's words, 1.733 from the compiled prompt, and 0.955 with the greybox control; the condition that holds framing best draws the described action least. Declaring the pose on 30 shots raises the action drawn from 58.9% to 74.4% without moving the framing. Transitions, fitted motion and human review of the generated panels remain open. Code: https://github.com/StudioPiLabs/pace-core
Commentsv2: the supplementary material referenced throughout v1 was never uploaded; it is removed and its 69 references resolved, two of its results moved into the main text and one dropped. 36 pages, 8 figures, 4 tables. Code: https://github.com/StudioPiLabs/pace-core
