Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object

TL;DR

This paper introduces Zero-P-to-3, a training-free method for reconstructing 3D objects from partial views, effectively generating consistent multi-view images and improving invisible region reconstruction.

Contribution

It proposes a novel fusion-based approach with iterative refinement that aligns priors in DDIM sampling for better partial-view 3D reconstruction without training.

Findings

Outperforms state-of-the-art methods on multiple datasets

Generates coherent multi-view images for invisible regions

Enhances reconstruction quality using geometric structures

Abstract

Generative 3D reconstruction shows strong potential in incomplete observations. While sparse-view and single-image reconstruction are well-researched, partial observation remains underexplored. In this context, dense views are accessible only from a specific angular range, with other perspectives remaining inaccessible. This task presents two main challenges: (i) limited View Range: observations confined to a narrow angular scope prevent effective traditional interpolation techniques that require evenly distributed perspectives. (ii) inconsistent Generation: views created for invisible regions often lack coherence with both visible regions and each other, compromising reconstruction consistency. To address these challenges, we propose \method, a novel training-free approach that integrates the local dense observations and multi-source priors for reconstruction. Our method introduces a fusion-based strategy to effectively align these priors in DDIM sampling, thereby generating multi-view consistent images to supervise invisible views. We further design an iterative refinement strategy, which uses the geometric structures of the object to enhance reconstruction quality. Extensive experiments on multiple datasets show the superiority of our method over SOTAs, especially in invisible regions.