iCreatAI News
Skip to content
Apple Machine Learning Research·· 2 days agoAI score26

Split-and-Scale Latent 3D Representations

Split-and-Scale Latent 3D Representations

AI summary

The authors propose split-and-scale, an inference-time method that expands latent capacity by applying a single pretrained tokenizer to arbitrarily small sub-regions of a 3D scene, since representing scenes as continuous functions of 3D coordinates lets the same latent capacity cover a smaller spatial extent and capture far higher detail. They conduct ablations on trade-offs between compute, memory, latent capacity, and reconstruction quality, showing the method achieves quality competitive with much larger models that exceed single-GPU memory limits. They also train an autoregressive 3D generator with split-and-scale that performs competitively with state-of-the-art baselines.

Source: Apple Machine Learning Research · machinelearning.apple.com