Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization

TL;DR

This paper introduces a three-stage framework for generating coherent and detailed 3D scenes from a single image, combining object recovery, spatial geometry inference, and layout optimization.

Contribution

It presents a novel method that explicitly models geometry and texture, improving scene coherence and object detail in single-image 3D scene generation.

Findings

Outperforms state-of-the-art in geometric accuracy

Achieves higher texture fidelity in generated models

Enhances scene layout synthesis quality

Abstract

In recent years, 3D generation has made great strides in both academia and industry. However, generating 3D scenes from a single RGB image remains a significant challenge, as current approaches often struggle to ensure both object generation quality and scene coherence in multi-object scenarios. To overcome these limitations, we propose a novel three-stage framework for 3D scene generation with explicit geometric representations and high-quality textural details via single image-guided model generation and spatial layout optimization. Our method begins with an image instance segmentation and inpainting phase, which recovers missing details of occluded objects in the input images, thereby achieving complete generation of foreground 3D assets. Subsequently, our approach captures the spatial geometry of reference image by constructing pseudo-stereo viewpoint for camera parameter estimation and scene depth inference, while employing a model selection strategy to ensure optimal alignment between the 3D assets generated in the previous step and the input. Finally, through model parameterization and minimization of the Chamfer distance between point clouds in 3D and 2D space, our approach optimizes layout parameters to produce an explicit 3D scene representation that maintains precise alignment with input guidance image. Extensive experiments on multi-object scene image sets have demonstrated that our approach not only outperforms state-of-the-art methods in terms of geometric accuracy and texture fidelity of individual generated 3D models, but also has significant advantages in scene layout synthesis.