WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

Amogh Joshi; Julian Ost; Felix Heide

cs.CVMar 31, 2026

WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

Authors: Amogh Joshi, Julian Ost, Felix Heide

Organizations: Princeton University · Torc Robotics

Abstract

Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a foundational property of flow matching - namely, defining a path of transport between two data distributions - we model 3D generation more generally as a problem of flowing through 3D data distributions, not limited to conditional denoising. We find that our latent-free flow approach generates causal and accurate 3D structure, and can use this as an intermediate distribution to guide the generation of more complex structure and high-quality texture - all while converging more rapidly than existing methods. We enable controllability over generated scenes with vectorized scene layout conditions for geometric structure control and visual texture control through scene attributes. We confirm the effectiveness of WorldFlow3D on both real outdoor driving scenes and synthetic indoor scenes, validating cross-domain generalizability and high-quality generation on real data distributions. We confirm favorable scene generation fidelity over approaches in all tested settings for unbounded scene generation. For more, see https://light.princeton.edu/worldflow3d.

Figures & tables

	XCube [ 31 ]	BlockFusion [ 42 ]	LidarDM [ 46 ]	LT3SD [ 24 ]	InfiniCube [ 23 ]	WorldGrow [ 18 ]	XScene [ 44 ]	Ours
Unbounded	✗	✓	✗	✓	✓	✓	✓	✓
Controllable	✗	✗	✗	✗	✓	✗	✗	✓
Cross-Domain	✓	✓	✗	✗	✗	✗	✗	✓
Texture	✗	✗	✗	✗	✓	✓	✓	✓

Table 1: Summary of recent 3D scene generation methods. Ours is the only approach satisfying all desirable criteria.

Figure 2: WorldFlow3D decomposes generation into a sequence of independent flows over progressively richer representations — transporting from noise, through coarse geometry into fine geometry, and visual appearance ( Sec. 3.1 ) . All flows operate directly in raw volumetric space ( Sec. 3.2 ), enabling a latent-free, hierarchical scene generation procedure. Generation is controlled by a vectorized geometric layout and discrete scene attributes, giving consistent structural and semantic control at every level ( Sec. 3.4 ).

Figure 3: Feather weighted velocity averaging in overlapping chunk regions significantly improves the generated geometry for unbounded generations, as shown above.

Figure 4: Qualitative comparison on outdoor scene generation with WorldFlow3D and baseline methods trained on the Waymo [ 37 ] dataset. We showcase scenes generated at moderate scales, and closer-up views of specific details including buildings and vehicles. We obtain high-quality, realistic geometry and smooth surfaces with a good amount of detail, as viewed from coherent building structure, smooth road surfaces, and distinct vehicle geometry.

Figure 5: Qualitative comparison on indoor scene generation with WorldFlow3D and baseline methods trained on the 3D-FRONT [ 12 ] dataset. We showcase generations of regions including (potentially multiple) rooms with various objects. Our generations are high-fidelity and contain smooth surfaces and realistic geometry.

	Method	COV $\uparrow$		MMD $\downarrow$		1-NNA $\downarrow$		JSD $\downarrow$	$\mathrm{FD}_{\textrm{C}}$ $\downarrow$
	Method	CD	EMD	CD	EMD	CD	EMD	JSD $\downarrow$	$\mathrm{FD}_{\textrm{C}}$ $\downarrow$
Waymo Uncond.	XCube [ 31 ]	27.50	24.90	19.75	2.99	95.85	85.35	0.480	214.08
	LidarDM [ 46 ]	15.30	15.40	29.74	3.60	99.40	98.10	0.564	232.49
	LT3SD [ 24 ]	20.00	16.10	34.33	3.96	95.85	85.35	0.524	76.04
	WorldFlow3D	33.00	32.70	16.57	2.81	89.15	70.15	0.490	74.83
Waymo Cond.	LidarDM [ 46 ]	12.00	11.30	35.46	3.81	99.60	99.20	0.590	215.49

Table 2: Quantitative Evaluation for Outdoor 3D Scene Generation on the Waymo Open Dataset [ 37 ] for WorldFlow3D and existing approaches. We show results for unconditional generation in the first section and conditional in the second. The best results for each metric are in bold ; second-best are underlined . We evaluate distribution coverage and alignment (COV, JSD), generation fidelity (MMD and 1-NNA), and feature-based distributional distance (

\mathrm{FD}_{\textrm{C}}

). We report metrics on large-scale scene sizes of

96m\times 96m

	Method	COV $\uparrow$		MMD $\downarrow$		1-NNA $\downarrow$		JSD $\downarrow$	$\mathrm{FD}_{\textrm{C}}$ $\downarrow$
	Method	CD	EMD	CD	EMD	CD	EMD	JSD $\downarrow$	$\mathrm{FD}_{\textrm{C}}$ $\downarrow$
3D-Front [ 12 ] Uncond.	BlockFusion [ 42 ]	29.00	28.40	0.054	0.221	91.50	90.65	0.380	165.46
	LT3SD [ 24 ]	23.40	26.20	0.056	0.223	93.00	91.60	0.230	44.97
	WorldGrow [ 18 ]	34.70	32.80	0.053	0.221	88.05	88.65	0.272	172.58
	WorldFlow3D	38.30	38.10	0.039	0.195	74.75	75.80	0.164	36.45

Table 3: Quantitative Evaluation for Indoor 3D Scene Generation on the synthetic 3D-FRONT [ 12 ] dataset. The best results for each metric are in bold ; second-best are underlined . We report metrics on small-scale scenes [ 24 , 42 ] of

2m\times 2m

Ablation	COV $\uparrow$		MMD $\downarrow$		1-NNA $\downarrow$		$\mathrm{FD}_{\textrm{C}}$ $\downarrow$	GPU-hrs $\downarrow$
Ablation	CD	EMD	CD	EMD	CD	EMD	$\mathrm{FD}_{\textrm{C}}$ $\downarrow$	GPU-hrs $\downarrow$
Latent Diffusion	37.75	33.75	7.426	1.801	91.38	75.63	120.87	288
Latent Flow	37.00	32.75	6.755	1.778	90.88	74.88	112.35	288
Flow from Noise	33.75	33.75	6.887	1.747	92.25	81.25	107.59	144
WorldFlow3D ( $p^{(f)}=p^{(1)}$ )	38.00	31.50	7.101	1.821	92.75	75.63	89.47	72
WorldFlow3D(full)	42.50	37.25	4.942	1.696	85.00	70.25	103.20	144

Table 4: Ablation Study over the core contributions of our method, comparing distribution coverage (COV), geometric fidelity (MMD and 1-NNA), visual texture quality (

\mathrm{FD}_{\textrm{C}})

, and training efficiency (GPU-hrs). We compare against traditional latent diffusion and latent flow approaches, followed by an ablation of our flow matching through distributions objective, and finally of our flow sequence hierarchy. We conduct our evaluation on the Waymo Open Dataset [ 37 ] , and the best results are bolded .

Figure 6: Ablation of Core Components. We provide qualitative results obtained by ablating the key components of our method. Latent diffusion and flow approaches produce structurally degenerate, non-realistic results, while flow from noise at finer distributions produces noisy outputs. Examples of this can be seen on the building walls, which are smooth with WorldFlow3D, and on vehicle details such as tires. Our hierarchical, latent-free approach is the only one that can produce high-quality, geometrically plausible results.

Figure 7: Visual Texture and Controllability. We report large-scale outdoor scenes with texture control via text attributes and geometry control via vector maps, yielding results conditioned on the same geometry to produce distinct environments.

Method	Rank	BT Score	95% CI	Win Rate
WorldFlow3D	1	0.692	[0.569, 0.813]	88%
XCube [ 31 ]	2	0.212	[0.118, 0.314]	63%
LT3SD [ 24 ]	3	0.085	[0.047, 0.131]	43%
LidarDM [ 46 ]	4	0.011	[0.004, 0.022]	6%

Table 5: User Study. We report Bradley-Terry (BT) [ 3 ] scores with 95% bootstrap confidence intervals and overall win rates.

3D Scene Generation

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

See all 190 papers

SpaceFlow: Locally Controllable 3D Generation
Oct 8, 2026Neil De La Fuente, Joan Lafuente, Mukhammadali Sayfiddinov +53D Shape Generation Text-to-3D Generation
ETH Zürich · Microsoft · Stanford University
OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder
Mar 17, 2026Sensen Gao, Zhaoqing Wang, Qihang Cao +53D Scene Generation 3D Diffusion Models
Mohamed bin Zayed University of Artificial Intelligence · AISphere · Shanghai Jiao Tong University +3
Lyra 2.0: Explorable Generative 3D Worlds
Apr 14, 2026Tianchang Shen, Sherwin Bahmani, Kai He +123D Scene Generation 3D-Aware Video Generation
NVIDIA

Oct 8, 2026J/K move · Enter open · S save

SpaceFlow: Locally Controllable 3D Generation

Neil De La Fuente, Joan Lafuente, Mukhammadali Sayfiddinov, Felicia Scharitzer+4

ETH Zürich · Microsoft · Stanford University

3D Shape Generation Text-to-3D Generation Part-Level 3D Generation

Open paper AskPDF arXiv

Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally. We present SpaceFlow, a training-free pipeline for locally controllable 3D generation from text descriptions and a collection of geometric primitives. Each primitive serves as a proxy for an object part and is assigned a local control level, enabling users to specify whether regions should strictly follow the input shape or allow generative completion. During structure generation, we enforce these spatial constraints within the generative flow process. For appearance synthesis, the generated structure is segmented and matched to the primitives. Each generated part is conditioned only on its assigned text or image cue, thereby limiting cross-part leakage. Regional geometry metrics demonstrate that SpaceFlow preserves the specified geometry in high-control regions and enables plausible shape variation in low-control areas. A user study further indicates that the resulting balance between geometric fidelity and generative freedom remains competitive in overall quality. When evaluating appearance on fixed geometry, text-conditioned routing achieves state-of-the-art prompt faithfulness and color/material accuracy. Qualitative results additionally show localized routing of image cues. The project page is available at SpaceFlow3D.github.io.

Abstract

3D Scene Generation

Explore similar work

SpaceFlow: Locally Controllable 3D Generation

OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder

Lyra 2.0: Explorable Generative 3D Worlds