MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

Hugging Face Daily Papers Papers
novel-view-synthesis monocular diffusion-models geometry-priors implicit-representations 3d-vision

Summary

MetaView proposes a diffusion-based monocular novel view synthesis framework that combines implicit geometry priors with metric depth guidance to achieve consistent and controllable rendering under large viewpoint changes from a single image.

Current visual generation models are capable of producing high-quality content, yet they lack a coherent perception of the spatial structure. Existing generative novel view synthesis methods typically introduce explicit geometry priors, which enforce spatial consistency but inherently restrict generalization in large view changes. In contrast, recent interactive generative methods favor implicit scene modeling, offering greater flexibility at the cost of precise camera control and geometry consistency. In this paper, we propose MetaView, a diffusion-based monocular novel view synthesis framework that enables rendering under large view changes from a single image. Our key insight is to combine implicit geometry modeling with minimal yet essential explicit 3D cues: we incorporate implicit geometry priors from a feed-forward geometry perception network to regularize structure without imposing restrictive reconstruction pipelines, while leveraging metric depth to anchor the generation to a metric scale. This design allows MetaView to achieve both geometry consistency and precise controllability. Extensive experiments demonstrate that, under challenging monocular large viewpoint changes, MetaView significantly outperforms existing methods and exhibits superior generalization. Our code is publicly available at https://github.com/KlingAIResearch/MetaView.
Original Article
View Cached Full Text

Cached at: 07/16/26, 05:42 AM

Paper page - MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

Source: https://huggingface.co/papers/2607.12000 Published on Jul 13

·

Submitted byhttps://huggingface.co/KaiiWuu1993

Wu Kaion Jul 16

Abstract

Currentvisualgenerationmodelsarecapableofproducinghigh-qualitycontent,yettheylackacoherentperceptionofthespatialstructure.Existinggenerativenovelviewsynthesismethodstypicallyintroduceexplicitgeometrypriors,whichenforcespatialconsistencybutinherentlyrestrictgeneralizationinlargeviewchanges.Incontrast,recentinteractivegenerativemethodsfavorimplicitscenemodeling,offeringgreaterflexibilityatthecostofprecisecameracontrolandgeometryconsistency.Inthispaper,weproposeMetaView,adiffusion-basedmonocularnovelviewsynthesisframeworkthatenablesrenderingunderlargeviewchangesfromasingleimage.Ourkeyinsightistocombineimplicitgeometrymodelingwithminimalyetessentialexplicit3Dcues:weincorporateimplicitgeometrypriorsfromafeed-forwardgeometryperceptionnetworktoregularizestructurewithoutimposingrestrictivereconstructionpipelines,whileleveragingmetricdepthtoanchorthegenerationtoametricscale.ThisdesignallowsMetaViewtoachievebothgeometryconsistencyandprecisecontrollability.Extensiveexperimentsdemonstratethat,underchallengingmonocularlargeviewpointchanges,MetaViewsignificantlyoutperformsexistingmethodsandexhibitssuperiorgeneralization.Ourcodeispubliclyavailableathttps://github.com/KlingAIResearch/MetaView.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2607\.12000

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

Models citing this paper1

#### Kwai-Kolors/MetaView

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.12000 in a dataset README.md to link it from this page.

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

InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Hugging Face Daily Papers

InfiniSplat presents a feed-forward single-image 3D Gaussian Splatting framework that uses geometry-guided sampling and query-conditioned implicit decoding to achieve surface-aligned Gaussian representation, improving large-baseline monocular view synthesis and generalizing from synthetic indoor training to open-world scenes.