PointDiT: Pixel-Space Diffusion Transformer for Monocular Geometry
google · hf · 2026-07-08
Google proposed PointDiT, which employs a pure ViT architecture to directly process 3D point map patches, combined with DINOv3 image tokens for conditional generation. While maintaining a minimalist architecture, this method surpasses complex latent-space models and demonstrates better robustness in ambiguous regions.
Related event: Google's PointDiT Recovers 3D Shapes from Single Images(2 posts)→
More from Research
- GigaChat Audio targets long-form audio grounding with timestamps across 120-minute inputs — ai-sage · 2026-07-21
- Paper models Transformer components as stochastic geometry and tests five architectures — Zhihua Liang · 2026-07-21
- LTX 2.3 LoRA demo changes a video’s camera angle — CQDSN · 2026-07-21
- OpenForecaster uses daily news to improve language-model forecasting — Cohere_Labs · 2026-07-21
- Baseten study finds new facts in LLM weights are fragile unless trained from many restatements — alex_verem · 2026-07-21
- uv-scripts/ocr returns to the top of Hugging Face datasets with a JSON model picker — vanstriendaniel · 2026-07-21