MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis

📅 2024-07-02
🏛️ IEEE Transactions on Pattern Analysis and Machine Intelligence
📈 Citations: 11
Influential: 0
📄 PDF

career value

165K/year
🤖 AI Summary
This work addresses the dual challenges of precise attribute control and cross-iteration consistency in multi-instance image generation. To this end, we propose (i) the MIGC++ controller, enabling text- or image-driven attribute control and bounding-box- or mask-driven spatial localization; and (ii) the Consistent-MIG algorithm, which preserves both unedited regions and instance identity across editing iterations. Our approach employs a divide-and-conquer single-instance diffusion architecture, cross-modal conditional injection, and iterative consistency regularization. We introduce two new benchmarks—COO-MIG and Multimodal-MIG—to rigorously evaluate multi-instance controllability. Extensive experiments on COCO-MIG, Multimodal-MIG, COCO-Position, and DrawBench demonstrate state-of-the-art performance, with significant improvements in positional accuracy, attribute fidelity, and the number of controllable instances. Notably, our method achieves, for the first time, unified fine-grained attribute isolation and stable iterative editing.

Technology Category

Application Category

📝 Abstract
We introduce the Multi-Instance Generation (MIG) task, which focuses on generating multiple instances within a single image, each accurately placed at predefined positions with attributes such as category, color, and shape, strictly following user specifications. MIG faces three main challenges: avoiding attribute leakage between instances, supporting diverse instance descriptions, and maintaining consistency in iterative generation. To address attribute leakage, we propose the Multi-Instance Generation Controller (MIGC). MIGC generates multiple instances through a divide-and-conquer strategy, breaking down multi-instance shading into single-instance tasks with singular attributes, later integrated. To provide more types of instance descriptions, we developed MIGC++. MIGC++ allows attribute control through text & images and position control through boxes & masks. Lastly, we introduced the Consistent-MIG algorithm to enhance the iterative MIG ability of MIGC and MIGC++. This algorithm ensures consistency in unmodified regions during the addition, deletion, or modification of instances, and preserves the identity of instances when their attributes are changed. We introduce the COCO-MIG and Multimodal-MIG benchmarks to evaluate these methods. Extensive experiments on these benchmarks, along with the COCO-Position benchmark and DrawBench, demonstrate that our methods substantially outperform existing techniques, maintaining precise control over aspects including position, attribute, and quantity.
Problem

Research questions and friction points this paper is trying to address.

Generate multiple instances in one image with precise attributes
Prevent attribute leakage between instances during generation
Maintain consistency when adding, deleting, or modifying instances
Innovation

Methods, ideas, or system contributions that make the work stand out.

Divide-and-conquer strategy for multi-instance generation
Text & image attribute control with position guidance
Consistent-MIG algorithm for iterative generation consistency
🔎 Similar Papers
No similar papers found.
D
Dewei Zhou
ReLER, CCAI, Zhejiang University, Hangzhou, China
Y
You Li
ReLER, CCAI, Zhejiang University, Hangzhou, China
F
Fan Ma
ReLER, CCAI, Zhejiang University, Hangzhou, China
Z
Zongxin Yang
ReLER, CCAI, Zhejiang University, Hangzhou, China
Y
Yi Yang
ReLER, CCAI, Zhejiang University, Hangzhou, China