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

Source: [MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation](<https://www.sota2.com/research/paper/69896a23c97a0b3e3b5dc572>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-10T05:00:04.897Z

Authors: Luoxi Zhang, Chun Xie, Itaru Kitahara

Published: 2026-02-05T20:07:46.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Reconstruction on Pix3D 10% of the data (test)](<https://www.sota2.com/research/sota/3d-reconstruction-on-pix3d-10-percent-of-the-data-test.md>): 3D Reconstruction; Pix3D 10% of the data (test); L1 CD (bed): 0.0172.

- [Single-view 3D Object Reconstruction on Pix3D 10% labeled data (S1)](<https://www.sota2.com/research/sota/single-view-3d-object-reconstruction-on-pix3d-10-percent-labeled-data-s1.md>): Single-view 3D Object Reconstruction; Pix3D 10% labeled data (S1); Chair Accuracy: 25.35.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.06163>)

[PDF](<https://arxiv.org/pdf/2602.06163.pdf>)
