# MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation

arXiv: https://arxiv.org/abs/2602.06163 · HTML: https://mlsanity.com/paper/2602.06163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](https://mlsanity.com/paper/1804.04610/) (2018)
- [Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images](https://mlsanity.com/paper/1901.11153/) (2019)
- [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://mlsanity.com/paper/1809.05068/) (2018)
- [3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow](https://mlsanity.com/paper/2203.15190/) (2022)
- [Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture](https://mlsanity.com/paper/2311.00457/) (2023)
- [Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors](https://mlsanity.com/paper/2209.15383/) (2022)
- [M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstruction](https://mlsanity.com/paper/2411.12635/) (2024)
- [Reflective Teacher: Semi-Supervised Multimodal 3D Object Detection in Bird's-Eye-View via Uncertainty Measure](https://mlsanity.com/paper/2412.04337/) (2024)
- [Semi-supervised Single-view 3D Reconstruction via Multi Shape Prior Fusion Strategy and Self-Attention](https://mlsanity.com/paper/2411.15420/) (2024)

## Abstract (arXiv)

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.