NVIDIA's Déjà View: 117M model loops one transformer block for 3D from photos
NVIDIAAI · x · 2026-11-14
NVIDIA released an interactive Hugging Face demo of Déjà View, which turns photos taken from different angles into 3D geometry and camera poses. The 117M-parameter model loops a single transformer block, matching or beating models up to 10x larger across five benchmarks with comparable or less compute; loop count is tunable to compute budget. NeurIPS 2026 oral paper plus code are available.
More from Multimodal
- Uncensored Qwen-Image-2.1 quantized model trends on Hugging Face — chatrlabs · 2026-11-14
- MiniMax H3 Image editing tested at 60MP: concept art to realistic photo in ~2 min on RTX 4090 — daroamer · 2026-11-14
- Maket launches Custom Materials: generate floor and wall textures from text or images — testingcatalog · 2026-11-14
- User shows off stunning Gemini-generated Milky Way hydrogen simulation — intellectronica · 2026-11-14
- AI-generated 4D Gaussian Splatting brings Scooby-Doo's Velma to life — buchachos · 2026-11-14
- Encoder-free multimodal LLMs re-learn encoder-like traits in early layers — rdesh26 · 2026-11-14