CCD-3DR: Consistent Conditioning in Diffusion for Single-Image 3D Reconstruction

TL;DR

This paper introduces CCD-3DR, a diffusion-based method for single-image 3D reconstruction that ensures consistent local feature conditioning, resulting in significantly improved accuracy over previous approaches.

Contribution

The paper proposes a centered diffusion probabilistic model that maintains point cloud stability and alignment with image features, enhancing 3D reconstruction quality.

Findings

Outperforms competitors by over 40% on ShapeNet-R2N2

Demonstrates robustness on real-world Pix3D dataset

Provides stable and consistent point cloud generation

Abstract

In this paper, we present a novel shape reconstruction method leveraging diffusion model to generate 3D sparse point cloud for the object captured in a single RGB image. Recent methods typically leverage global embedding or local projection-based features as the condition to guide the diffusion model. However, such strategies fail to consistently align the denoised point cloud with the given image, leading to unstable conditioning and inferior performance. In this paper, we present CCD-3DR, which exploits a novel centered diffusion probabilistic model for consistent local feature conditioning. We constrain the noise and sampled point cloud from the diffusion model into a subspace where the point cloud center remains unchanged during the forward diffusion process and reverse process. The stable point cloud center further serves as an anchor to align each point with its corresponding local projection-based features. Extensive experiments on synthetic benchmark ShapeNet-R2N2 demonstrate that CCD-3DR outperforms all competitors by a large margin, with over 40% improvement. We also provide results on real-world dataset Pix3D to thoroughly demonstrate the potential of CCD-3DR in real-world applications. Codes will be released soon