T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

Hugging Face Daily Papers Papers
3d-reconstruction generative-models surface-reconstruction multi-view computer-vision mesh-generation

Summary

T3lescope提出一种单一固定分辨率生成器的推理时粗到细级联方法，从多视角图像实现跨尺度（从单物体到大型户外场景）的任意分辨率高保真3D场景网格重建，无需逐场景优化，在室内、户外和城市规模场景上超越了前馈与生成基线。

We reconstruct high-fidelity 3D scene meshes from posed multi-view images without per-scene optimization, across scales ranging from single objects to large outdoor scenes. Per-scene optimization methods lack the learned 3D prior needed when observations are sparse or surfaces are glossy or transparent. Existing generative methods leverage such priors to complete geometry in sparsely observed regions, but typically operate at a fixed resolution over a limited spatial extent, trading spatial coverage against detail. Reconstructing a large scene therefore often requires partitioning it into independently processed overlapping local regions, making it difficult to maintain global geometric consistency. To address these issues, we propose T3lescope, which applies a single fixed-resolution generator across scene scales in an inference-time coarse-to-fine cascade. A coarse level establishes the scene layout, and finer levels perturb and denoise geometry inherited from the coarser level within progressively finer spatial cells to recover surface detail. The model is trained on individual cells at multiple scales and shares its weights across all levels, so no hierarchy is fixed during training, and the number of levels, cell scales, and cell locations are determined at inference time. On indoor, outdoor, and city-scale scenes, T3lescope outperforms feed-forward and generative baselines, matches or surpasses per-scene optimization, and recovers fine structures as well as glossy and transparent surfaces. These results show that our method generalizes across diverse scenes, view counts, and image resolutions. Project page: https://pfnet-research.github.io/t3lescope/
Original Article
View Cached Full Text

Cached at: 10/13/26, 06:44 AM

Paper page - T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

Source: https://huggingface.co/papers/2610.03308

Abstract

Wereconstructhigh-fidelity3Dscenemeshesfromposedmulti-viewimageswithoutper-sceneoptimization,acrossscalesrangingfromsingleobjectstolargeoutdoorscenes.Per-sceneoptimizationmethodslackthelearned3Dpriorneededwhenobservationsaresparseorsurfacesareglossyortransparent.Existinggenerativemethodsleveragesuchpriorstocompletegeometryinsparselyobservedregions,buttypicallyoperateatafixedresolutionoveralimitedspatialextent,tradingspatialcoverageagainstdetail.Reconstructingalargescenethereforeoftenrequirespartitioningitintoindependentlyprocessedoverlappinglocalregions,makingitdifficulttomaintainglobalgeometricconsistency.Toaddresstheseissues,weproposeT3lescope,whichappliesasinglefixed-resolutiongeneratoracrossscenescalesinaninference-timecoarse-to-finecascade.Acoarselevelestablishesthescenelayout,andfinerlevelsperturbanddenoisegeometryinheritedfromthecoarserlevelwithinprogressivelyfinerspatialcellstorecoversurfacedetail.Themodelistrainedonindividualcellsatmultiplescalesandsharesitsweightsacrossalllevels,sonohierarchyisfixedduringtraining,andthenumberoflevels,cellscales,andcelllocationsaredeterminedatinferencetime.Onindoor,outdoor,andcity-scalescenes,T3lescopeoutperformsfeed-forwardandgenerativebaselines,matchesorsurpassesper-sceneoptimization,andrecoversfinestructuresaswellasglossyandtransparentsurfaces.Theseresultsshowthatourmethodgeneralizesacrossdiversescenes,viewcounts,andimageresolutions.Projectpage:https://pfnet-research.github.io/t3lescope/

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2610\.03308

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/2610.03308 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.03308 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.03308 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World

Hugging Face Daily Papers

WorldRecon 提出一种生成式多视角网格重建框架，可从无位姿 RGB 图像重建大规模 3D 场景的完整网格。它将 TRELLIS.2 生成模型与重建式条件架构结合，通过邻域感知潜在修补和因果世界生成保证场景级一致性，在合成与真实室内场景上分别将 Chamfer 距离降低 14.9% 和 43.1%，达到最先进性能。

Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Hugging Face Daily Papers

Sat3DGen introduces a geometry-first approach for generating street-level 3D scenes from a single satellite image, achieving improved geometric accuracy and photorealism through novel constraints and training strategies. The method demonstrates significant improvements over prior work on the VIGOR-OOD benchmark.

Structured 3D Latents for Scalable and Versatile 3D Generation

Papers with Code Trending

微软提出统一的结构化潜在表示（SLAT），结合 rectified flow transformers 实现高质量、多格式（Radiance Fields、3D Gaussians、网格）的 3D 资产生成，支持文本/图像条件及局部编辑，在 500K 3D 数据集上训练的 2B 参数模型显著超越现有方法。

SUPRA-TEX: 3D Generation with Super-Aligned Texture

Hugging Face Daily Papers

SUPRA-Tex 提出通过解耦可见材质估计、表面对齐与观测引导的3D补全来生成可重光照的3D材质，在单图3D生成中实现可见区域的高保真还原与未观测表面的连贯补全，在纹理化和端到端资产生成任务上达到SOTA。