NAMVIS (NeurIPS 2026): next-scale autoregression beats diffusion for novel-view synthesis, 3x faster
RexDouglass · x · 2026-10-09
NAMVIS (NeurIPS 2026) replaces slow iterative diffusion denoising with next-scale autoregression for novel-view synthesis.
- Generates consistent novel views from sparse posed inputs, coarse-to-fine, with camera geometry injected at every scale (Multi-scale ProPE) plus dual-path conditioning
- Over 3x faster: NAMVIS 1B runs 0.6s per view vs 2.1-2.6s for baselines, with PSNR 21.766 / LPIPS 0.102 vs Zero-1-to-3 XL's 17.199 / 0.194 and EscherNet's 18.574 / 0.157
- Evaluated on Objaverse, GSO, and OmniObject3D
Related event: NAMVIS Replaces Diffusion with Autoregression for 3x Faster View Synthesis(2 posts)→
More from Multimodal
- Hugging Face Speech-to-Speech adds Persian ASR and TTS support — andimarafioti · 2026-10-09
- ComfyUI app ANIMA goes viral: Qwen 3.5 'hallucinates' popular photos, 300K views — Ok_Contribution8157 · 2026-10-09
- fal Engineer on Video Speed: H3 Max Renders 15 Seconds of Video in 5 — OdinLovis · 2026-10-09
- Odyssey launches Odyssey-3, claims SOTA world model on Physics-IQ benchmark — Scobleizer · 2026-10-09
- One prompt, one full movie: dev shows multi-director agent pipeline for AI films — Exciting-Income-5840 · 2026-10-09
- Nano Banana 2.1 becomes Google's best image editing model across all 7 edit actions — ArtificialAnlys · 2026-10-09