Video models replace NeRF/3DGS pipelines: single-frame novel view synthesis, open-source soon
jonstephens85 · x · 2026-10-24
Researcher zhiwenfan showed video generation models now handle much of what once required fitting NeRF or 3DGS to many photos.
- Given a single frame, their model predicts what you'd see as you move through a scene, even inside a painting
- The team says it will open-source the model and eval protocol, with details to come
More from Multimodal
- Stunning AI-Generated Sci-Fi Scene: Futuristic Car Rides Toward a Floating Tower — ciguleva · 2026-10-24
- Community fine-tune fixes Qwen-Image 2.1 VAE 8-pixel grid artifact — Crazy-Repeat-2006 · 2026-10-24
- Character LoRA trained on 21 images fails across models—training setup questioned — IntrovertedOtaku03 · 2026-10-24
- Tencent's Hy-Nomas video world model ported to native ComfyUI, runs on 12GB VRAM — LatentSpacer · 2026-10-24
- Recreating PS2-Era Harry Potter With FastH3-V2 in 4 Steps — aziib · 2026-10-24
- A Full AI Music Video Made Locally on DGX Spark With MiniMax H3 — Ornery-Block-3522 · 2026-10-24