From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis

TL;DR

NAS3R is a self-supervised framework that jointly learns 3D geometry and camera parameters from 2D images without annotations, using a novel transformer-based approach and Gaussian formulation.

Contribution

It introduces NAS3R, a novel self-supervised 3D reconstruction method that integrates explicit geometry and camera prediction without ground-truth data.

Findings

NAS3R outperforms existing self-supervised methods in 3D reconstruction quality.

The framework effectively reconstructs 3D from uncalibrated, unposed images.

NAS3R is compatible with supervised architectures and can incorporate priors.

Abstract

In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D Gaussians from uncalibrated and unposed context views and renders target views using its self-predicted camera parameters, enabling self-supervised training from 2D photometric supervision. To ensure stable convergence, NAS3R integrates reconstruction and camera prediction within a shared transformer backbone regulated by masked attention, and adopts a depth-based Gaussian formulation that facilitates well-conditioned optimization. The framework is compatible with state-of-the-art supervised 3D reconstruction architectures and can incorporate pretrained priors or intrinsic information when available. Extensive experiments show that NAS3R achieves superior results to other self-supervised methods, establishing a scalable and geometry-aware paradigm for 3D reconstruction from unconstrained data. Code and models are publicly available at https://ranrhuang.github.io/nas3r/.