SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-07-05 with 3 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Geonung Kim et al. |
| Year | 2026 |
| HF Upvotes | 3 |
| arXiv | 2607.04540 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
Geometry-conditioned 3D scene generation enables 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 a view schedule, then synthesizes multi-view observations along the scheduled views, and finally reconstructs a 3D representation from the generated images. However, defining the view schedule becomes 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 a directed generation graph whose nodes represent anchor views and whose edges represent interpolation 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 through object-level conditioning, assigning each object an identity image for appearance guidance and a geometry-adherence parameter for region-wise control over the input geometry. Experiments demonstrate that SceneFrom3D achieves state-of-the-art geometry-conditioned outdoor 3D scene generation, producing high-quality scenes with controllable object appearance and geometry adherence.
Engineering Breakdown
The Problem
However, defining the view schedule becomes 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.
The Approach
To address this bottleneck, we present SceneFrom3D, a framework that automatically schedules views from outdoor input geometries.
Key Results
Experiments demonstrate that SceneFrom3D achieves state-of-the-art geometry-conditioned outdoor 3D scene generation, producing high-quality scenes with controllable object appearance and geometry adherence.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Scenefrom3d
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::