GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation

TL;DR

GALA introduces a geometry-aware, sparse, and adaptive 3D shape representation that efficiently captures detailed surfaces, enabling fast fitting and high-quality generative modeling with diffusion schemes.

Contribution

The paper presents GALA, a novel 3D shape representation combining sparsity, adaptivity, and local geometry-awareness for improved detail and efficiency in 3D generation.

Findings

Fitted to objects in less than 10 seconds.

Supports efficient flattening and manipulation with transformer networks.

Enables detailed 3D shape generation with a cascaded pipeline.

Abstract

We propose GALA, a novel representation of 3D shapes that (i) excels at capturing and reproducing complex geometry and surface details, (ii) is computationally efficient, and (iii) lends itself to 3D generative modelling with modern, diffusion-based schemes. The key idea of GALA is to exploit both the global sparsity of surfaces within a 3D volume and their local surface properties. Sparsity is promoted by covering only the 3D object boundaries, not empty space, with an ensemble of tree root voxels. Each voxel contains an octree to further limit storage and compute to regions that contain surfaces. Adaptivity is achieved by fitting one local and geometry-aware coordinate frame in each non-empty leaf node. Adjusting the orientation of the local grid, as well as the anisotropic scales of its axes, to the local surface shape greatly increases the amount of detail that can be stored in a given amount of memory, which in turn allows for quantization without loss of quality. With our optimized C++/CUDA implementation, GALA can be fitted to an object in less than 10 seconds. Moreover, the representation can efficiently be flattened and manipulated with transformer networks. We provide a cascaded generation pipeline capable of generating 3D shapes with great geometric detail.