CityLift: Compositional 3D Urban Generation from a Single Image

Haoran Gong; Jie Feng; Chenxu Wang

cs.CVOct 23, 2026

CityLift: Compositional 3D Urban Generation from a Single Image

Authors: Haoran Gong, Jie Feng, Chenxu Wang

Organizations: School of Software Engineering, Xi’an Jiaotong University · Zhongguancun Academy, Beijing, China

Abstract

Generating editable 3D urban scenes from a single image requires detailed building assets with a coherent spatial arrangement. Occlusion and perspective ambiguity make it difficult to infer complete building geometry together with consistent relative scales and positions. We present CityLift, a framework that generates individual textured building meshes from an urban image by coupling scene-level spatial modeling with building-level synthesis. CityLift first learns building shape and placement jointly through coupled scene and instance streams, producing coarse sparse structures in a common coordinate system. We then introduce generative spatial inheritance, which maps each building's coarse occupancy and scene-conditioned 3D feature field into a local volume to guide a flow model that generates finer structure. The same coordinate mapping places the generated meshes back into the scene, preserving their spatial relationship to the scaffold. To address the scarcity of urban data pairing scene images with individual 3D buildings, we construct CityLift-5K, comprising 4,997 synthetic scenes with instance masks, building meshes, and placement annotations. Experiments on CityLift-5K and scene blocks from UrbanScene3D and InstanceBuilding demonstrate improved building geometry and scene composition. The project page is available at https://ranhaogong.github.io/CityLift/.

Figures & tables

Figure 2: Overview of CityLift. Given a single urban image and building instance masks, CityLift generates individually editable building meshes in a shared scene frame. (a) A shared scene–instance generator predicts coarse occupancy in a common scene frame, implicitly modeling building placement, scale, and geometry. (b) A scaffold-derived coordinate map $T_{i}$ deterministically resamples occupancy and contextual features $F_{i}$ into each building’s local volume, forming the aligned condition $A_{i}$ . (c) Conditioned on $A_{i}$ and building image features $e_{i}$ , a local flow model regenerates finer sparse structures from noise. These structures guide mesh generation, and the resulting buildings are mapped back into the scene using the inherited transforms.

Method	CD $\downarrow$	Acc $\downarrow$	Comp $\downarrow$	F@1 $\uparrow$	F@2 $\uparrow$	CD $\downarrow$	Acc $\downarrow$	Comp $\downarrow$	F@1 $\uparrow$	F@2 $\uparrow$	Runtime $\downarrow$ (s/scene)
	Building level					Scene level					Runtime $\downarrow$ (s/scene)
TRELLIS.2	—	—	—	—	—	3.327	3.274	3.380	0.318	0.517	39.2
SAM 3D	2.761	2.565	2.956	0.397	0.595	2.595	2.501	2.689	0.387	0.597	83.7
Pixal3D	2.547	2.206	2.889	0.396	0.603	2.617	2.306	2.928	0.380	0.592	1482.4
3D-Fixer	2.701	2.533	2.870	0.403	0.602	2.832	2.853	2.811	0.385	0.590	310.3
SceneGen	9.352	10.092	8.612	0.126	0.223	4.973	4.795	5.151	0.214	0.368	231.9

Table 1: Geometric evaluation on CityLift-5K. An em dash denotes unavailable building-level output.

Figure 3: Qualitative comparison on blocks extracted from CityLift-5K testset. We slightly adjust the viewing angle to better showcase the generated scenes.

	Building level					Scene level
Method	CD $\downarrow$	Acc $\downarrow$	Comp $\downarrow$	F@1 $\uparrow$	F@2 $\uparrow$	CD $\downarrow$	Acc $\downarrow$	Comp $\downarrow$	F@1 $\uparrow$	F@2 $\uparrow$
TRELLIS.2	—	—	—	—	—	2.809	2.766	2.851	0.401	0.616
SAM 3D	1.789	1.794	1.785	0.576	0.776	2.112	2.112	2.111	0.466	0.685
Pixal3D	1.490	1.303	1.678	0.600	0.818	2.067	1.666	2.469	0.473	0.693
3D-Fixer	1.797	1.497	2.098	0.489	0.708	2.507	1.973	3.042	0.422	0.641
SceneGen	13.376	13.634	13.118	0.083	0.158	8.017	5.566	10.467	0.147	0.248

Table 2: External evaluation on UrbanScene3D. Quantitative comparison on blocks extracted from a synthetic urban scene, assessing the geometric accuracy of individual buildings and assembled scenes.

	Building level					Scene level
Method	CD $\downarrow$	Acc $\downarrow$	Comp $\downarrow$	F@1 $\uparrow$	F@2 $\uparrow$	CD $\downarrow$	Acc $\downarrow$	Comp $\downarrow$	F@1 $\uparrow$	F@2 $\uparrow$
TRELLIS.2	—	—	—	—	—	3.667	3.324	4.009	0.200	0.385
SAM 3D	1.995	2.421	1.570	0.366	0.620	2.418	2.887	1.949	0.351	0.594
Pixal3D	1.768	1.720	1.816	0.428	0.711	2.012	2.116	1.909	0.422	0.694
3D-Fixer	1.983	2.186	1.780	0.369	0.637	2.192	2.403	1.982	0.387	0.648
SceneGen	10.321	10.835	9.807	0.098	0.195	5.801	6.034	5.567	0.178	0.325

Table 3: External evaluation on InstanceBuilding. Quantitative comparison on scene blocks from real-world reconstructed meshes, assessing the geometric accuracy of individual buildings and assembled scenes.

Figure 4: Qualitative comparison on blocks extracted from UrbanScene3D and InstanceBuilding. We slightly adjust the viewing angle to better showcase the generated scenes.

Method	L	G	A	M	Overall
TRELLIS.2	84.2	75.2	71.7	74.8	77.6
SAM 3D	80.8	67.9	69.2	68.3	72.8
Pixal3D	79.6	64.2	63.8	64.6	69.5
3D-Fixer	80.8	65.8	58.5	65.6	69.6
SceneGen	44.0	55.8	53.1	54.8	51.0
Ours	87.3	81.2	77.9	81.7	82.8

Table 4: MLLM-as-a-judge visual evaluation on UrbanScene3D. ChatGPT 6 Astra scores the input image and four rendered views of each output. Results are averaged over all blocks shared by all six methods. All values are on a 0–100 scale, with higher values better. L, G, A, and M denote layout and completeness, shape and proportion, appearance and detail, and multi-view structural quality.

	Building		Scene
Method	CD $\downarrow$	F@2 $\uparrow$	CD $\downarrow$	F@2 $\uparrow$
Coarse decoding	1.15	0.85	1.22	0.84
w/o scene guidance	3.22	0.35	2.59	0.46
w/o aligned injection	2.51	0.47	2.41	0.50
w/o hidden-feature injection	2.21	0.56	2.17	0.58
w/o occupancy injection	1.18	0.85	1.26	0.83

Table 5: Quantitative results of the ablation study on CityLift-5K.

Figure 5: Qualitative results of the ablation study.

3D Scene Generation

3D scene generation creates structured, explorable environments from text, images, maps, or other inputs.

See all 190 papers

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Oct 17, 2025Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai +63D Reconstruction 3D Scene Generation
National Yang Ming Chiao Tung University · UIUC · University of Zaragoza +1
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
Jul 6, 2026Paul Engstler, Iro Laina, Christian Rupprecht +13D Scene Generation 3D Scene Layout Generation
Visual Geometry Group, University of Oxford
InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image
Jul 4, 2026Gwanhyeong Koo, Hyunsu Kim, Youngji Kim +53D Scene Generation 3D Scene Layout Generation
1KAIST · *Work done during an internship at NAVER LABS. · 2NAVER LABS +1

Oct 17, 2025J/K move · Enter open · S save

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang+5

National Yang Ming Chiao Tung University · UIUC · University of Zaragoza+1

3D Reconstruction 3D Scene Generation Image-to-3D Scene Generation Urban Scene Reconstruction

Open paper AskPDF arXiv

Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task for immersive and embodied applications. The challenge lies in the lack of large-scale and high-quality real-world 3D scans for training generalizable generative models. In this paper, we take an alternative route to create large-scale 3D scenes by leveraging readily available satellite imagery for realistic coarse geometry and open-domain diffusion models for high-quality close-up appearance synthesis. We propose Skyfall-GS, a novel hybrid framework that synthesizes immersive city-block scale 3D urban scenes by combining satellite reconstruction with diffusion refinement, eliminating the need for costly 3D annotations, and also featuring real-time, immersive 3D exploration. We tailor a curriculum-driven iterative refinement strategy to progressively enhance geometric completeness and photorealistic texture. Extensive experiments demonstrate that Skyfall-GS provides improved cross-view consistent geometry and more realistic textures compared to state-of-the-art approaches. Project page: https://skyfall-gs.jayinnn.dev/

Abstract

3D Scene Generation

Explore similar work

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image