PLACID：基于视频扩散与合成轨迹的身份保持多物体合成
PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories
把预训练 I2V 扩散模型的时序先验当作多物体合成的『布局收敛机制』：随机初始化物体位置，让模型在视频帧序列中把它们平滑移动到目标布局，取最后一帧作为合成结果；这套『合成轨迹数据 + 末帧取图』的范式可迁移到任何需要多元素一致排布的可控生成任务。
原文依据 we leverage a pretrained image-to-video (I2V) diffusion model with text control to preserve objects consistency
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式人工智能的最新进展大幅提升了照片级真实感的图像合成能力，但在影棚级的多物体合成任务上仍显不足。该任务要求同时满足：(i) 近乎完美地保持每个物品的身份特征，(ii) 精确的背景与色彩保真度，(iii) 对布局与设计元素的控制，(iv) 完整且美观地展示全部物体。然而，当前最优模型往往会改变物体细节、遗漏或重复物体，并产生相对尺寸错误或物品呈现方式不一致的布局。为弥补这一差距，我们提出 PLACID，一个将一组物体图像转换为美观多物体合成结果的框架。我们的方法有两项主要贡献。第一，我们利用一个带文本控制的预训练图像到视频（I2V）扩散模型，通过挖掘视频中的时序先验来保持物体一致性、身份特征与背景细节。第二，我们提出一种新颖的数据整理策略，生成合成序列，其中随机放置的物体平滑移动到其目标位置。这些合成数据在训练时与视频模型的时序先验相契合。在推理阶段，随机位置初始化的物体会在文本引导下一致地收敛为连贯布局，最后一帧即作为合成图像。大量定量评估与用户研究表明，PLACID 在多物体合成任务上优于最优方法，在身份、背景与色彩保持方面表现更佳，遗漏物体更少，结果在视觉上更具吸引力。
英文原文摘要 1621 字符
Recent advances in generative AI have dramatically improved photorealistic image synthesis, yet they fall short for studio-level multi-object compositing. This task demands simultaneous (i) near-perfect preservation of each item's identity, (ii) precise background and color fidelity, (iii) layout and design elements control, and (iv) complete, appealing displays showcasing all objects. However, current state-of-the-art models often alter object details, omit or duplicate objects, and produce layouts with incorrect relative sizing or inconsistent item presentations. To bridge this gap, we introduce PLACID, a framework that transforms a collection of object images into an appealing multi-object composite. Our approach makes two main contributions. First, we leverage a pretrained image-to-video (I2V) diffusion model with text control to preserve objects consistency, identities and background details by exploiting temporal priors from videos. Second, we propose a novel data curation strategy that generates synthetic sequences where randomly placed objects smoothly move to their target positions. This synthetic data aligns with the video model's temporal priors during training. At inference, objects initialized at random positions consistently converge into coherent layouts guided by text, with the final frame serving as the composite image. Extensive quantitative evaluations and user studies demonstrate that PLACID surpasses state-of-the-art methods in multi-object compositing, achieving superior identity, background, and color preservation, with less omitted objects and visually appealing results.