Paper Detail

NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

Ramil Khafizov, Ilya Statsenko, Ruslan Rakhimov, Artem Komarichev, Peter Wonka, Evgeny Burnaev

huggingface Score 6.0

Published 2026-10-03 · First seen 2026-10-08

General AI

Abstract

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 this generation process to explicit camera geometry, we propose Multi-scale Projective Pose Encoding, which injects source and target camera transformations into both target-view self-attention and source-to-target cross-attention at every resolution. NAMVIS further combines global conditioning with dense geometry-aware cross-attention, enabling the model to preserve source-view appearance while maintaining target-view consistency. Across Objaverse, GSO, and OmniObject3D, NAMVIS outperforms diffusion-based baselines in PSNR, SSIM, and LPIPS, while running over 3 times faster than the evaluated diffusion baselines under the same evaluation setting. These results suggest that geometry-conditioned next-scale autoregression is a promising and efficient alternative to diffusion for sparse-view multi-view synthesis. Additional qualitative results, videos, and resources are available at https://corl-team.github.io/namvis/

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{khafizov2026namvis,
  title = {NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis},
  author = {Ramil Khafizov and Ilya Statsenko and Ruslan Rakhimov and Artem Komarichev and Peter Wonka and Evgeny Burnaev},
  year = {2026},
  abstract = {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 s},
  url = {https://huggingface.co/papers/2610.04722},
  keywords = {code available, huggingface daily},
  eprint = {2610.04722},
  archiveprefix = {arXiv},
}

Metadata

{}