MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914308738252800 |
|---|---|
| author | Zhang, Luoxi Xie, Chun Kitahara, Itaru |
| author_facet | Zhang, Luoxi Xie, Chun Kitahara, Itaru |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06163 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation Zhang, Luoxi Xie, Chun Kitahara, Itaru Computer Vision and Pattern Recognition 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. |
| title | MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.06163 |