PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories

TL;DR

PLACID is a novel framework that uses video diffusion models and synthetic data to produce high-quality, identity-preserving multi-object composites with accurate layouts and visual fidelity.

Contribution

It introduces a new approach combining pretrained video diffusion models with synthetic data curation for improved multi-object compositing.

Findings

Outperforms state-of-the-art in identity and background preservation

Produces more accurate object layouts and sizes

Achieves higher user satisfaction in evaluations

Abstract

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.