用少量标注数据+大量无标注图像，提升3D重建质量
MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation
- 通过自适应更新与SDF感知伪标签加权，优化半监督学习
- 在Pix3D上降低20.61%的Chamfer Distance，IoU提升24.09%
- 适合资源有限但需高质量3D重建的研究者
基于隐式SDF的单视角3D重建方法虽能生成高质量表面，但依赖大规模标注数据，限制了可扩展性。本文提出MetaSSP，一种新颖的半监督框架，充分利用大量无标注图像。该方法引入基于梯度的参数重要性估计以正则化自适应EMA更新，并设计结合增强一致性与SDF方差的SDF感知伪标签加权机制。从10%的有监督预热开始，统一管道协同优化有标签与无标签数据。在Pix3D基准测试中，相比现有半监督基线，本方法将Chamfer Distance降低约20.61%，IoU提升约24.09%，达到新性能上限。
原文摘要 · Abstract (English)
Implicit SDF-based methods for single-view 3D reconstruction achieve high-quality surfaces but require large labeled datasets, limiting their scalability. We propose MetaSSP, a novel semi-supervised framework that exploits abundant unlabeled images. Our approach introduces gradient-based parameter importance estimation to regularize adaptive EMA updates and an SDF-aware pseudo-label weighting mechanism combining augmentation consistency with SDF variance. Beginning with a 10% supervised warm-up, the unified pipeline jointly refines labeled and unlabeled data. On the Pix3D benchmark, our method reduces Chamfer Distance by approximately 20.61% and increases IoU by around 24.09% compared to existing semi-supervised baselines, setting a new state of the art.
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。