GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Summary
The paper introduces GAE, a geometry-native autoencoder that creates a compact latent space for generating 3D-consistent scenes, enhancing visual quality and coherence over existing methods.
View Cached Full Text
Cached at: 09/23/26, 03:30 AM
Paper page - GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Source: https://huggingface.co/papers/2609.24981
Abstract
Wepresentacompactgeometry-nativelatentspaceasasharedfoundationforperceptionandgeneration.Visualgeneratorscanproducephotorealisticframeswithoutpreservingaconsistent3Dscene.Wearguethatthisisnotonlyamodelingproblembutalsoarepresentationproblem:generatorstypicallyevolveappearance-centriclatents,whileperceptionmodelsrecovergeometryinasemanticallyrichspacethatencodescross-viewstructure.Ratherthanaddinggeometryasanotheroutput,wereparameterizeageometryfoundationmodel’sfeaturesintoacompactlatentspaceforgeneration.Werealizethisshiftwiththegeometry-nativeautoencoder(GAE),whoselatentisjointlydecodabletoappearance,depth,cameras,andpointmaps.Withthisstate,astandardconditionalflowsupportsdiversegenerationtasks.Incontrolledcomparisonsthatholdthegeneratorandtrainingprotocolfixed,replacingthelatentwithGAEimprovesbothvisualqualityandindependentlymeasured3Dcoherence:FVDfallsby12.7%and23.1%onRealEstate10KandDL3DV,andcamera-trajectoryerrorishalvedonRealEstate10K.Together,theseresultsshowthatthelatentspaceiscentraltogeometry-consistentgenerationandcanserveasasharedinterfacebetweenperceptionandgeneration.
View arXiv pageView PDFProject pageGitHub120Add to collection
Get this paper in your agent:
hf papers read 2609\.24981
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.24981 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.24981 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.24981 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation
CGGS is a text-to-3D framework that improves geometric consistency and quality in ego-centric 3D scene generation using a multi-stage approach with consistency-augmented loss, layout decoration, and geometric refinement via entropy-based depth loss.
Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex Domains
The paper proposes GeoLAMP, a geometry-aware latent autoregressive generative model for solving multiphysics partial differential equations in complex geometries, using a dual-encoder architecture and causal self-attention transformer with flow matching for stable and scalable predictions.
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
This paper proposes GASP, a framework that injects geometric priors into vision-language models via deep supervision with contrastive and depth consistency losses, achieving significant improvements on 3D spatial reasoning benchmarks without using 3D VQA data.
@zhiwen_fan_: paper from dust3r’s team
A paper from the DUSt3R team proposes sparse auto-regressive modeling for 3D scene generation from multi-view images, using a voxel-aligned 3D latent space and an occupancy-aware masked autoregressive transformer.
AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling
This paper introduces AeroJEPA, a Joint-Embedding Predictive Architecture for scalable 3D aerodynamic field modeling. It addresses limitations in current surrogate models by predicting semantic latent representations of flow fields, enabling efficient high-fidelity analysis and design optimization.