2025/04/28 by Xinyang Li, Yi C, Li, Xinyang +11 · 2 citations
Computer Science · #Amodal perception #Computer Vision and Pattern Recognition (cs.CV) #Control (management) #FOS: Computer and information sciences #Face recognition and analysis #Fidelity #Generalization #Generative Adversarial Networks and Image Synthesis #Generative model #Image (mathematics) #Image Enhancement Techniques #Inpainting #Pipeline (software) #Prior probability
paper · pdf · doi:10.48550/arxiv.2504.19506
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Image deocclusion (or amodal completion) aims to recover the invisible regions (\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of high-quality data that balances diversity, plausibility, and fidelity remains a major obstacle. To address this challenge, we identify three critical elements: leveraging in-the-wild image data for diversity, incorporating human expertise for plausibility, and utilizing generative priors for fidelity. We propose SynergyAmodal, a novel framework for co-synthesizing in-the-wild amodal datasets with comprehensive shape and appearance annotations, which integrates these elements through a tripartite data-human-model collaboration. First, we design an occlusion-grounded self-supervised learning algorithm to harness the diversity of in-the-wild image data, fine-tuning an inpainting diffusion model into a partial completion diffusion model. Second, we establish a co-synthesis pipeline to iteratively filter, refine, select, and annotate the initial deocclusion results of the partial completion diffusion model, ensuring plausibility and fidelity through human expert guidance and prior model constraints. This pipeline generates a high-quality paired amodal dataset with extensive category and scale diversity, comprising approximately 16K pairs. Finally, we train a full completion diffusion model on the synthesized dataset, incorporating text prompts as conditioning signals. Extensive experiments demonstrate the effectiveness of our framework in achieving zero-shot generalization and textual controllability. Our code, dataset, and models will be made publicly available at https://github.com/imlixinyang/SynergyAmodal.