NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

  • 类型：arxiv
  • 标识：2610.04722
  • 链接：https://arxiv.org/abs/2610.04722
  • 主分类：multimodal
  • 形态：method
  • TLDR：Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at inference time. We introduce NAMVIS, a diffusion-free framework that reformulates multi-view image synthesis as geometry-conditioned next-scale autoregression. Instead of generating target views through repeated denoising, NAMVIS predicts discrete visual tokens through a small number of coarse-to-fine scale steps, while sampling all tokens within each scale and across target views in parallel. To anchor thi
  • 待LLM分类：否
  • 标题中文：NAMVIS：下一尺度自回归多视图图像合成
  • TLDR中文：稀疏视图新视角合成是三维内容创作中的核心问题，但基于扩散的方法受迭代去噪限制，多视图生成在推理时开销高昂。本文提出 NAMVIS，一种无扩散框架，将多视图图像合成重新表述为几何条件下的下一尺度自回归过程。NAMVIS 不通过反复去噪生成目标视图，而是通过少量由粗到细的尺度步预测离散视觉 token，并在同一尺度内以及跨目标视图间并行采样所有 token。为锚定此过程……
  • 来源文件：
  • /inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json