CVLGMar 17, 2022

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation

arXiv:2203.09516v3298 citationsh-index: 45
Originality Highly original
AI Analysis

This work addresses 3D shape inference for computer vision and graphics applications, offering a unified approach that outperforms specialized methods.

The authors tackled the problem of multimodal 3D shape tasks like completion, reconstruction, and generation by proposing an autoregressive prior for 3D shapes, achieving state-of-the-art performance across these tasks.

Powerful priors allow us to perform inference with insufficient information. In this paper, we propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation. We model the distribution over 3D shapes as a non-sequential autoregressive distribution over a discretized, low-dimensional, symbolic grid-like latent representation of 3D shapes. This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e.g., generating a complete chair given only a view of the back leg). We also show that the learned autoregressive prior can be leveraged for conditional tasks such as single-view reconstruction and language-based generation. This is achieved by learning task-specific naive conditionals which can be approximated by light-weight models trained on minimal paired data. We validate the effectiveness of the proposed method using both quantitative and qualitative evaluation and show that the proposed method outperforms the specialized state-of-the-art methods trained for individual tasks. The project page with code and video visualizations can be found at https://yccyenchicheng.github.io/AutoSDF/.

Code Implementations1 repo
Foundations

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

Your Notes