CVApr 4, 2024

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

arXiv:2404.03656v141 citationsh-index: 45CVPR
Originality Incremental advance
AI Analysis

This addresses the challenge of 3D consistency in generative models for computer vision, offering a more efficient alternative to distillation-based approaches.

The paper tackles the problem of single-view 3D inference by directly generating multi-view-consistent RGB-D images, resulting in more accurate synthesis and geometry compared to state-of-the-art methods.

We present MVD-Fusion: a method for single-view 3D inference via generative modeling of multi-view-consistent RGB-D images. While recent methods pursuing 3D inference advocate learning novel-view generative models, these generations are not 3D-consistent and require a distillation process to generate a 3D output. We instead cast the task of 3D inference as directly generating mutually-consistent multiple views and build on the insight that additionally inferring depth can provide a mechanism for enforcing this consistency. Specifically, we train a denoising diffusion model to generate multi-view RGB-D images given a single RGB input image and leverage the (intermediate noisy) depth estimates to obtain reprojection-based conditioning to maintain multi-view consistency. We train our model using large-scale synthetic dataset Obajverse as well as the real-world CO3D dataset comprising of generic camera viewpoints. We demonstrate that our approach can yield more accurate synthesis compared to recent state-of-the-art, including distillation-based 3D inference and prior multi-view generation methods. We also evaluate the geometry induced by our multi-view depth prediction and find that it yields a more accurate representation than other direct 3D inference approaches.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes