Apple proposes HeadsUp for large-scale 3D Gaussian head reconstruction using 10k+ subject dataset
rsasaki0109 · x · 2026-08-16
Apple proposes HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from multi-camera setups.
It uses an encoder-decoder architecture to compress views into a latent representation, decoded into UV-parameterized 3D Gaussians anchored to a neutral template. This decouples Gaussian count from input resolution, enabling training with many high-res views.
Trained on an internal dataset of over 10,000 subjects—an order of magnitude larger than existing datasets—it achieves state-of-the-art reconstruction performance.
More from Multimodal
- ImageNet should retire: DiT method rankings negatively correlate between ImageNet and text-to-image — YouJiacheng · 2026-10-16
- Open-source anatomy-reveal skill turns Claude into an exploded-view motion design studio — msharmas · 2026-10-16
- Flux 3 Klein vs Flux 2 Klein hands-on: the new base model 'barely usable' for T2I — Both-Rub5248 · 2026-10-16
- USTC paper uses speculative sampling to cut latency in interactive video generation — ustc · 2026-10-16
- 800,000 Gaussian splats run in WebGPU; Casado sees near-infinite scaling — generativist · 2026-10-16
- Nano Banana 2.1 image generation now live in Perplexity Computer for all users — ChrisUniverse · 2026-10-16