SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control
Summary
SceneFrom3D is a framework that automatically schedules views from input geometry to generate high-quality outdoor 3D scenes with object-level control over appearance and geometry adherence.
View Cached Full Text
Cached at: 07/09/26, 07:52 AM
Paper page - SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control
Source: https://huggingface.co/papers/2607.04540
Abstract
SceneFrom3D generates 3D outdoor scenes by automatically scheduling views from input geometry and controlling object appearance and geometry adherence through identity images and geometry-adherence parameters.
Geometry-conditioned3D scene generationenables the creation of 3D environments from user-provided geometry, offering direct control over scene structure and object layout. To generate such 3D scenes, current methods commonly adopt a three-stage design that first defines aview schedule, then synthesizesmulti-view observationsalong the scheduled views, and finally reconstructs a 3D representation from the generated images. However, defining theview schedulebecomes a major bottleneck for outdoor scenes, where large, unstructured, and unbounded geometry makes it difficult to obtain views that provide sufficient coverage while supporting stable generation. To address this bottleneck, we present SceneFrom3D, a framework that automatically schedules views from outdoor input geometries. SceneFrom3D constructs adirected generation graphwhose nodes representanchor viewsand whose edges representinterpolation trajectories, defining which views to synthesize, which view pairs to interpolate, and in which order generation should proceed. Beyond automatic view scheduling, SceneFrom3D further improves controllability throughobject-level conditioning, assigning each object anidentity imagefor appearance guidance and ageometry-adherence parameterfor region-wise control over the input geometry. Experiments demonstrate that SceneFrom3D achieves state-of-the-art geometry-conditioned outdoor3D scene generation, producing high-quality scenes with controllable object appearance and geometry adherence.
View arXiv pageView PDFProject pageGitHub1Add to collection
Get this paper in your agent:
hf papers read 2607\.04540
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/2607.04540 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.04540 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.04540 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
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
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.
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.
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
Introduces SpaR3D-MoE, an end-to-end framework for adaptive 3D spatial reasoning from sparse RGB views, using manifold sampling and geometry-inductive mixture-of-experts to achieve state-of-the-art performance on VSI-Bench, ScanQA, and SQA3D.
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
Introduces GARD, a diffusion-based framework that operates in the feature space of a feed-forward 3D reconstructor to jointly recover scene geometry and high-quality imagery from degraded inputs.
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
SynCity 3000 introduces a framework for generating large, globally coherent 3D scenes by adapting image-to-3D generators as convolutional operators, fine-tuned on synthetic scene data from a new data engine.