超越重组：含缺失部件的碎裂物体恢复
Beyond Reassembly: Fractured Object Recovery with Missing Parts
把碎片重组与缺失部件补全统一进一个 Transformer 框架，用 missing token 表示缺失部件并与已有部件特征做关联推理，这个「缺失 token + 跨部件特征关联」的设定可直接迁移到点云/网格补全、遮挡物体重建等任务。
原文依据 correlating features of both existing and missing parts using a transformer, where the latter is naturally represented as missing tokens
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出一项新的基于学习的任务，名为碎裂物体恢复。与以往仅通过重叠区域对齐现有部件的碎裂物体重组任务不同，本任务旨在不仅重组互不相关的部件，还预测缺失部件，从而恢复完整形状。本任务与实际经验相符：借助相似形状的先验知识，即使是不重叠的部件也能被推理到合适的位置。我们还提出了该任务的首个学习模型，利用 Transformer 关联现有部件与缺失部件的特征，其中后者自然地表示为缺失 token。为便于开展该任务，我们在现有碎裂物体基准的基础上，通过施加不同配置的缺失部件，引入了一个新的数据集。我们进行了大量评估，以展示所提模型相对于基线的性能。结果表明，联合进行部件重组与预测是可行的，并且二者具有相互促进的效果，我们相信这能够启发未来研究并有利于实际应用。
英文原文摘要 1124 字符
We propose a novel learning-based task named fractured object recovery. Unlike the previous fractured object reassembly task that only aligns existing parts with overlaps, our task aims to recover the complete shape by not only reassembling irrelevant parts but also predicting missing parts. Our task coincides with practical experiences, where the prior knowledge of similar shapes can be leveraged such that even non-overlapping parts can be reasoned into adequate locations. We also present the first learning model for the proposed task by correlating features of both existing and missing parts using a transformer, where the latter is naturally represented as missing tokens. To facilitate the task, we introduce a new dataset based on the existing fractured object benchmark by imposing different configurations of missing parts. We perform extensive evaluations to demonstrate the performance of the proposed model over baselines. The results show that joint part reassembly and prediction can be made possible and also have mutual benefits, which we believe can inspire future research and favor real applications.