← 返回论文检索
ACM Multimedia 2025Content: Vision and Language

CEARI: Co-Evolutionary Agents for Reassembling and Inpainting Puzzles with Gaps and Missing Pieces

Xingke Song, Jianxu Shangguan, Yiran Li 0003, Jialu Zhang 0003, Jianfeng Ren, Ruibin Bai, Xin Chen 0003, Xudong Jiang 0001

PDF 由论文原始站点提供,PaperCompass 不保存论文文件。DOI 10.1145/3746027.3754695 ↗

摘要

Puzzle solving has recently become a popular research topic. Existing solvers often overlook puzzles with missing pieces. The missing pieces, together with gaps between pieces, pose significant challenges, amplified by a large solution space. To tackle the challenges, we propose Co-Evolutionary Agents for Reassembling and Inpainting (CEARI), one agent to inpaint missing contents and the other to reassemble the puzzle, with a shared perception network to perceive the puzzle status. The reassembly agent utilizes an evolutionary algorithm to explore the large solution space, to discover a sequence of fragment-swapping actions to efficiently reassemble the puzzle, while the inpainting agent evolves from using a local outpainting network at the early stage to using a global inpainting network at the latter stage. Furthermore, a co-evolutionary training paradigm is designed to iteratively evolve the two agents in a coherent and collaborative manner, improving reassembly accuracy and inpainting quality simultaneously. Experimental results on three datasets show that CEARI largely outperforms state-of-the-art methods in terms of both reassembly accuracy and inpainting quality.