ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes
This addresses the scalability issue in 3D shape representation for perception and robotics tasks, though it appears incremental as it builds on existing implicit representation methods.
The paper tackles the problem of efficiently encoding large datasets of 3D shapes by introducing ROAD, a recursive implicit octree auto-decoder that achieves state-of-the-art reconstruction results with a compression ratio above 99%.
Compact and accurate representations of 3D shapes are central to many perception and robotics tasks. State-of-the-art learning-based methods can reconstruct single objects but scale poorly to large datasets. We present a novel recursive implicit representation to efficiently and accurately encode large datasets of complex 3D shapes by recursively traversing an implicit octree in latent space. Our implicit Recursive Octree Auto-Decoder (ROAD) learns a hierarchically structured latent space enabling state-of-the-art reconstruction results at a compression ratio above 99%. We also propose an efficient curriculum learning scheme that naturally exploits the coarse-to-fine properties of the underlying octree spatial representation. We explore the scaling law relating latent space dimension, dataset size, and reconstruction accuracy, showing that increasing the latent space dimension is enough to scale to large shape datasets. Finally, we show that our learned latent space encodes a coarse-to-fine hierarchical structure yielding reusable latents across different levels of details, and we provide qualitative evidence of generalization to novel shapes outside the training set.