NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

Hugging Face Daily Papers Papers
multi-view-synthesis autoregressive-models 3d-vision novel-view-synthesis camera-geometry diffusion-free efficiency

Summary

NAMVIS proposes a diffusion-free framework that reformulates sparse-view multi-view image synthesis as geometry-conditioned next-scale autoregression, using Multi-scale Projective Pose Encoding to anchor generation to camera geometry. It outperforms diffusion baselines on Objaverse, GSO, and OmniObject3D in PSNR/SSIM/LPIPS while running over 3x faster.

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/
Original Article
View Cached Full Text

Cached at: 10/08/26, 12:10 PM

Paper page - NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

Source: https://huggingface.co/papers/2610.04722

Abstract

Sparse-viewnovelviewsynthesisisacentralproblemin3Dcontentcreation,butdiffusion-basedapproachesremainlimitedbyiterativedenoising,makingmulti-viewgenerationexpensiveatinferencetime.WeintroduceNAMVIS,adiffusion-freeframeworkthatreformulatesmulti-viewimagesynthesisasgeometry-conditionednext-scaleautoregression.Insteadofgeneratingtargetviewsthroughrepeateddenoising,NAMVISpredictsdiscretevisualtokensthroughasmallnumberofcoarse-to-finescalesteps,whilesamplingalltokenswithineachscaleandacrosstargetviewsinparallel.Toanchorthisgenerationprocesstoexplicitcamerageometry,weproposeMulti-scaleProjectivePoseEncoding,whichinjectssourceandtargetcameratransformationsintobothtarget-viewself-attentionandsource-to-targetcross-attentionateveryresolution.NAMVISfurthercombinesglobalconditioningwithdensegeometry-awarecross-attention,enablingthemodeltopreservesource-viewappearancewhilemaintainingtarget-viewconsistency.AcrossObjaverse,GSO,andOmniObject3D,NAMVISoutperformsdiffusion-basedbaselinesinPSNR,SSIM,andLPIPS,whilerunningover3timesfasterthantheevaluateddiffusionbaselinesunderthesameevaluationsetting.Theseresultssuggestthatgeometry-conditionednext-scaleautoregressionisapromisingandefficientalternativetodiffusionforsparse-viewmulti-viewsynthesis.Additionalqualitativeresults,videos,andresourcesareavailableathttps://corl-team.github.io/namvis/

View arXiv pageView PDFProject pageGitHub5Add to collection

Get this paper in your agent:

hf papers read 2610\.04722

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### smileyenot983/NAMVIS Image-to-Image• Updatedabout 2 hours ago • 2

Datasets citing this paper2

#### smileyenot983/objaversexl_sketchfab_pmap #### smileyenot983/objaversexl_github6.5_pmap

Spaces citing this paper1

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space

Hugging Face Daily Papers

GeoVerse is a framework for synthesizing world-consistent novel views by performing generation in a geometric latent space from a 3D foundation model and injecting appearance priors from a video generative model, demonstrating improved visual quality and geometric consistency over existing methods.