Apple Machine Learning Research·· 2 d agoAI score35
Apple Split-and-Scale Expands Latent 3D Representation Capacity at Inference
Split-and-Scale Latent 3D Representations
AI summary
Apple researchers propose split-and-scale, a method that expands the latent capacity of 3D representations at inference time while keeping training cost tractable. By applying a single pretrained tokenizer to arbitrarily small sub-regions of a scene, it allocates the same latent capacity to a smaller spatial extent and captures far higher detail. The approach matches the quality of much larger models that exceed single-GPU memory limits, and an autoregressive 3D generator trained on it performs competitively with state-of-the-art baselines.
Source:Apple Machine Learning Research · machinelearning.apple.com