通过测试时训练，分步修复破损形状，提升重建精度。
3D Shape Completion with Test-Time Training
- 分步预测破损与恢复部分，保持二者关联性
- 在ShapeNet上8类形状的Chamfer距离显著降低
- 适合需要高精度3D重建的研究者
本文研究3D形状补全问题，即通过预测缺失部分来恢复不完整形状。不同于以往一步完成修复的方法，本文将破损部分与新生成部分的预测分开处理，但确保两者相互关联。采用受DeepSDF启发的解码器网络，支持测试时训练——在推理阶段微调网络参数以更精确匹配输入的不完整形状。此前方法常在断裂边界产生伪影，而本文通过过拟合于破损区域，显著提升了在ShapeNet数据集上八类不同形状的重建效果，以Chamfer距离衡量有明显改进。
原文摘要 · Abstract (English)
This work addresses the problem of \textit{shape completion}, i.e., the task of restoring incomplete shapes by predicting their missing parts. While previous works have often predicted the fractured and restored shape in one step, we approach the task by separately predicting the fractured and newly restored parts, but ensuring these predictions are interconnected. We use a decoder network motivated by related work on the prediction of signed distance functions (DeepSDF). In particular, our representation allows us to consider test-time-training, i.e., finetuning network parameters to match the given incomplete shape more accurately during inference. While previous works often have difficulties with artifacts around the fracture boundary, we demonstrate that our overfitting to the fractured parts leads to significant improvements in the restoration of eight different shape categories of the ShapeNet data set in terms of their chamfer distances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。