Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting

Jiawei Zhang, Youmin Zhang, Fabio Tosi, Meiying Gu, Jiahe Li, Xiaohan Yu, Jin Zheng, Xiao Bai, Matteo Poggi

Keywords: surface reconstruction, 3d gaussian splatting

TL;DR: This paper presents Eve3D, jointly optimizing 3d gaussian splatting with prior depth maps to efficiently reconstruct accurate surfaces.

Abstract:

We present Eve3D, a novel framework for dense 3D reconstruction based on 3D
Gaussian Splatting (3DGS). While most existing methods rely on imperfect priors
derived from pre-trained vision models, Eve3D fully leverages these priors by
jointly optimizing both them and the 3DGS backbone. This joint optimization
creates a mutually reinforcing cycle: the priors enhance the quality of 3DGS, which
in turn refines the priors, further improving the reconstruction. Additionally, Eve3D
introduces a novel optimization step based on bundle adjustment, overcoming the
limitations of the highly local supervision in standard 3DGS pipelines. Eve3D
achieves state-of-the-art results in surface reconstruction and novel view synthesis
on the Tanks & Temples, DTU, and Mip-NeRF360 datasets. while retaining fast
convergence, highlighting an unprecedented trade-off between accuracy and speed.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 14521