AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations
This work addresses the problem of improving 3D shape reconstruction quality and generalization for computer vision and graphics applications, representing an incremental advance with a novel method for a known bottleneck.
The paper tackles 3D reconstruction from point clouds by introducing AIR-Nets, an attention-based framework that encodes point clouds into local and global latent vectors to predict occupancy values, achieving state-of-the-art results on ShapeNet and generalizing well to FAUST in zero-shot settings.
This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds. Since representing 3D shapes in a local and modular fashion increases generalization and reconstruction quality, AIR-Nets encode an input point cloud into a set of local latent vectors anchored in 3D space, which locally describe the object's geometry, as well as a global latent description, enforcing global consistency. Our model is the first grid-free, encoder-based approach that locally describes an implicit function. The vector attention mechanism from [Zhao et al. 2020] serves as main point cloud processing module, and allows for permutation invariance and translation equivariance. When queried with a 3D coordinate, our decoder gathers information from the global and nearby local latent vectors in order to predict an occupancy value. Experiments on the ShapeNet dataset show that AIR-Nets significantly outperform previous state-of-the-art encoder-based, implicit shape learning methods and especially dominate in the sparse setting. Furthermore, our model generalizes well to the FAUST dataset in a zero-shot setting. Finally, since AIR-Nets use a sparse latent representation and follow a simple operating scheme, the model offers several exiting avenues for future work. Our code is available at https://github.com/SimonGiebenhain/AIR-Nets.