DepthTile: Depth-Guided Existing-Image Self-Tiling with Input-Side Tileability Assessment

Rui Wang; Xi Chen; Hui Dai; Piaopiao Yu; Yixue Hao; Long Hu; Min Chen

cs.CVOct 12, 2026

DepthTile: Depth-Guided Existing-Image Self-Tiling with Input-Side Tileability Assessment

Authors: Rui Wang, Xi Chen, Hui Dai, Piaopiao Yu, Yixue Hao, Long Hu, Min Chen

Organizations: School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China · Nanjing University of Aeronautics and Astronautics · School of Computer Science and Engineering, South China University of Technology

Abstract

Existing-image self-tiling aims to transform a given image into a seamlessly repeatable tile while preserving its original semantics and local details. This task requires weak editing to retain the source but leave periodic seams, whereas strong editing improves tileability at the large risk of content drift.Existing diffusion-based tiling pipelines alleviate boundary discontinuities, yet lack awareness of which regions are geometrically important to preserve. In this work, we propose DepthTile, a depth-guided self-tiling method whose generation module requires no retraining of the diffusion backbone. It converts monocular depth into a spatial preservation prior and integrates it into the timestep-dependent masking mechanism of Tiled Diffusion. DepthTile converts depth into a spatial editability map and fuses it with the differential diffusion mask. This strengthens source preservation in near-field regions indicated by the monocular depth prior while retaining editing flexibility near compatible background boundaries. To access when self-tiling is feasible, we introduce the Self-Tiling Ability Score (STAS), a lightweight input-side predictor based on RGB, gradient, depth, and depth-gradient cues. On a 335-image benchmark, relative to the default Tiled Diffusion pipeline, DepthTile reduces MAE, LPIPS, and Tiling Score by 12.8%, 26.7%, and 8.4%, respectively. STAS reliably enables difficulty-aware analysis and further supports compatibility-aware pairwise image tiling.

Figures & tables

Figure 1: Qualitative and quantitative illustration of the preservation–tileability trade-off. (a) Direct concatenation, Tiled Diffusion ( Madar and Fried 2025 ) , and DepthTile on a representative input. (b) Mean MAE and Tiling Score of all compared methods. DepthTile preserves local structures while achieving the lowest mean MAE and Tiling Score.

Figure 2: Overview of DepthTile. (a) Depth-guided iterative tiling generation converts monocular depth into timestep-dependent masks that mix source and generated latents; the inset compares the input with the tileable output. (b) Self-tiling assessment encodes RGB and depth boundary cues with a lightweight MLP to predict $\phi_{\mathrm{STAS}}$ .

Method	MAE $\downarrow$	RMSE $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	DISTS $\downarrow$	TS $\downarrow$	GSE $\downarrow$
Asymmetric Tiling SD ( tjm35 2022 )	0.1356	0.1926	0.3278	0.4562	0.2232	0.2332	0.3341
Seamless Tile Inpainting ( brick2face 2023 )	0.0561	0.1153	0.7519	0.1173	0.0771	0.2010	0.3261
MultiDiffusion ( Bar-Tal et al. 2023 )	0.1091	0.1606	0.4036	0.3683	0.1831	0.2402	0.3173
Spot Diffusion ( Frolov, Moser, and Dengel 2025 )	0.2261	0.3078	0.2519	0.5842	0.1686	0.1683	0.2797
Tiled Diffusion ( Madar and Fried 2025 )	0.0508	0.0856	0.6622	0.1134	0.0804	0.0670	0.3464
DepthTile (ours)	0.0443	0.0740	0.6976	0.0831	0.0648	0.0614	0.3074

Table 1: Quantitative comparison of existing-image self-tiling methods on the 335-image benchmark. We report content-preservation and seam-quality metrics. Best and second-best results are shown in bold and underlined , respectively.

Mask Prior	MAE $\downarrow$	RMSE $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	DISTS $\downarrow$	TS $\downarrow$	GSE $\downarrow$
Tiled Diffusion	0.0508	0.0856	0.6622	0.1134	0.0804	0.0670	0.3464
Uniform	0.1631	0.2255	0.2665	0.6396	0.3778	0.0765	0.5627
Edge-only	0.1302	0.1986	0.4102	0.4003	0.2575	0.0757	0.5064
Saliency-only	0.3724	0.4560	0.1291	0.7938	0.4480	0.0816	0.8995
Depth-only	0.0927	0.1468	0.4923	0.3206	0.2029	0.0641	0.3641
DepthTile (ours)	0.0443	0.0740	0.6976	0.0831	0.0648	0.0614	0.3074

Table 2: Comparison of spatial mask priors under an otherwise identical Tiled Diffusion pipeline, isolating uniform, edge, saliency, and depth cues. Best and second-best results are shown in bold and underlined , respectively.

Figure 3: Qualitative comparison of existing-image self-tiling methods. Columns show the input and outputs from direct concatenation, DepthTile, Tiled Diffusion, MultiDiffusion, and Spot Diffusion; yellow boxes mark enlarged regions. DepthTile better preserves fine structures while reducing visible tiling artifacts.

Depth Estimator	Params (M) $\downarrow$	MAE $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	DISTS $\downarrow$	TS $\downarrow$	GSE $\downarrow$	Time (s) $\downarrow$
Depth Anything V2-S	24.8	0.0469	0.6834	0.0941	0.0702	0.0641	0.3091	3.338
MiDaS DPT-Hybrid	123.0	0.0466	0.6851	0.0928	0.0694	0.0634	0.3079	3.353
ZoeDepth-N	$\sim$ 345	0.0443	0.6976	0.0831	0.0648	0.0614	0.3074	3.698

Table 3: Effect of the monocular depth estimator on DepthTile. Output quality, model size, and inference time are compared under identical tiling settings. Best and second-best results are shown in bold and underlined , respectively.

Subset	Method	MAE $\downarrow$	RMSE $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	DISTS $\downarrow$	TS $\downarrow$	GSE $\downarrow$
All pairs	Tiled Diffusion	0.0403	0.0725	0.7489	0.0862	0.0505	0.1349	0.2789
All pairs	DepthTile	0.0355	0.0649	0.7722	0.0638	0.0425	0.1621	0.2812
Top-50 STAS	Tiled Diffusion	0.0305	0.0594	0.8402	0.0592	0.0430	0.0830	0.1305
Top-50 STAS	DepthTile	0.0272	0.0549	0.8532	0.0438	0.0376	0.1019	0.1219

Table 5: Quantitative comparison of Tiled Diffusion and DepthTile for pairwise tiling on 100 image pairs and the top-50 pairs selected by Pairwise STAS. Best and second-best results within each subset are shown in bold and underlined , respectively.

Figure 5: STAS-stratified self-tiling performance. DepthTile consistently reduces MAE and TS across all difficulty levels.

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Component	Setting
Backbone	SDXL base and refiner, FP16
Depth estimator	ZoeDepth-N
Input/output tile	$512\times 512$ RGB
Scheduler	EulerDiscreteScheduler
Denoising steps	40
Base/refiner split	0.8

Appendix

Table 6: Reproducible inference configuration used for the horizontal self-tiling experiments in the ZoeDepth depth-strength sweep.

Category	$N$	Category	$N$
Animals	32	Architecture	41
Beach	26	Desert	17
Forest	24	Garden	30
Indoor	31	Landscape	33
Mountain	29	Object foreground	35
Road	17	Street	20

Appendix

Table 7: Semantic composition of the 335-image benchmark used in all horizontal self-tiling experiments.

Split	$N$	MAE $\downarrow$	RMSE $\downarrow$	PCC $\uparrow$	SRCC $\uparrow$
Validation	50	0.0930	0.1111	0.2914	0.3424
Test	51	0.0810	0.1003	0.6147	0.7184

Appendix

Table 8: Prediction accuracy and rank correlation of the retained four-feature STAS head on the validation and held-out test splits.

$\alpha_{D}$	MAE $\downarrow$	RMSE $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	DISTS $\downarrow$	TS $\downarrow$	GSE $\downarrow$
0.00	0.05079 $\pm$ 0.01787	0.08557 $\pm$ 0.02579	0.66219 $\pm$ 0.11733	0.11338 $\pm$ 0.03934	0.08043 $\pm$ 0.02095	0.06705 $\pm$ 0.03817	0.34638 $\pm$ 0.14384
0.05	0.05046 $\pm$ 0.01785	0.08489 $\pm$ 0.02578	0.66349 $\pm$ 0.11741	0.11143 $\pm$ 0.03935	0.07904 $\pm$ 0.02013	0.06542 $\pm$ 0.03686	0.34048 $\pm$ 0.14327
0.10	0.05017 $\pm$ 0.01780	0.08427 $\pm$ 0.02570	0.66469 $\pm$ 0.11742	0.11001 $\pm$ 0.03917	0.07846 $\pm$ 0.02020	0.06497 $\pm$ 0.03694	0.33459 $\pm$ 0.14191
0.15	0.04996 $\pm$ 0.01775	0.08384 $\pm$ 0.02563	0.66582 $\pm$ 0.11748	0.10871 $\pm$ 0.03912	0.07807 $\pm$ 0.02001	0.06464 $\pm$ 0.03690	0.33145 $\pm$ 0.14110
0.20	0.04975 $\pm$ 0.01771	0.08337 $\pm$ 0.02557	0.66680 $\pm$ 0.11744	0.10779 $\pm$ 0.03898	0.07748 $\pm$ 0.01973	0.06448 $\pm$ 0.03711	0.32671 $\pm$ 0.14150
0.25	0.04955 $\pm$ 0.01767	0.08294 $\pm$ 0.02553	0.66793 $\pm$ 0.11735	0.10664 $\pm$ 0.03894	0.07723 $\pm$ 0.01965	0.06519 $\pm$ 0.03881	0.32369 $\pm$ 0.14135

Appendix

Table 9: Complete depth-fusion-strength sweep on the 335-image benchmark. Values are mean

\pm

population standard deviation over the same 335 inputs.

$\alpha_{D}$	$\gamma$	MAE $\downarrow$	RMSE $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	DISTS $\downarrow$	TS $\downarrow$	GSE $\downarrow$
0.20	0.35	0.05001 $\pm$ 0.01776	0.08385 $\pm$ 0.02564	0.66563 $\pm$ 0.11751	0.10921 $\pm$ 0.03912	0.07829 $\pm$ 0.02029	0.06498 $\pm$ 0.03767	0.33047 $\pm$ 0.14049
0.20	0.50	0.05011 $\pm$ 0.01777	0.08407 $\pm$ 0.02566	0.66518 $\pm$ 0.11746	0.10964 $\pm$ 0.03893	0.07834 $\pm$ 0.02023	0.06489 $\pm$ 0.03744	0.33226 $\pm$ 0.14079
0.20	0.75	0.05022 $\pm$ 0.01778	0.08432 $\pm$ 0.02567	0.66473 $\pm$ 0.11744	0.11032 $\pm$ 0.03886	0.07850 $\pm$ 0.02018	0.06526 $\pm$ 0.03721	0.33480 $\pm$ 0.14119
0.20	1.00	0.05031 $\pm$ 0.01781	0.08451 $\pm$ 0.02572	0.66431 $\pm$ 0.11745	0.11081 $\pm$ 0.03891	0.07885 $\pm$ 0.02017	0.06576 $\pm$ 0.03750	0.33675 $\pm$ 0.14164
1.00	0.35	0.04604 $\pm$ 0.01681	0.07670 $\pm$ 0.02452	0.68766 $\pm$ 0.11516	0.09120 $\pm$ 0.03462	0.06838 $\pm$ 0.01800	0.06636 $\pm$ 0.03872	0.30763 $\pm$ 0.13399
1.00	0.50	0.04676 $\pm$ 0.01699	0.07794 $\pm$ 0.02475	0.68355 $\pm$ 0.11585	0.09428 $\pm$ 0.03560	0.07018 $\pm$ 0.01850	0.06703 $\pm$ 0.03989	0.30910 $\pm$ 0.13476

Appendix

Table 10: Sensitivity to the depth-shaping exponent

\gamma

. Values are mean

\pm

population standard deviation over 335 images.

Category	$N$	$\Delta$ MAE	$\Delta$ RMSE	$\Delta$ SSIM	$\Delta$ LPIPS	$\Delta$ DISTS
animals	32	-0.00614 (-14.0%)	-0.01140 (-14.9%)	+0.03213 (+4.4%)	-0.02731 (-29.1%)	-0.01134 (-20.6%)
architecture	41	-0.00664 (-13.0%)	-0.01186 (-13.6%)	+0.03598 (+5.2%)	-0.02775 (-27.9%)	-0.01541 (-19.4%)
beach	26	-0.00573 (-13.1%)	-0.01080 (-14.2%)	+0.03325 (+4.9%)	-0.02827 (-27.5%)	-0.01467 (-17.9%)
desert	17	-0.00536 (-12.3%)	-0.00980 (-13.5%)	+0.03276 (+4.8%)	-0.02823 (-27.0%)	-0.02293 (-23.5%)
forest	24	-0.00824 (-11.4%)	-0.01351 (-12.0%)	+0.04606 (+8.3%)	-0.03794 (-24.0%)	-0.01738 (-18.1%)
garden	30	-0.00749 (-11.0%)	-0.01273 (-11.6%)	+0.03754 (+6.8%)	-0.03496 (-24.6%)	-0.01500 (-17.1%)

Appendix

Table 11: Category-wise change from Tiled Diffusion (

\alpha_{D}=0

) to DepthTile (

\alpha_{D}=1

) for content-preservation metrics. Each cell gives the absolute change followed by the relative change in parentheses.

Category	$N$	$\Delta$ TS	$\Delta$ GSE
animals	32	+0.00106 (+2.3%)	-0.02988 (-10.5%)
architecture	41	-0.00350 (-5.2%)	-0.04242 (-11.4%)
beach	26	-0.01107 (-17.6%)	-0.03044 (-10.5%)
desert	17	-0.01736 (-24.5%)	-0.03967 (-13.5%)
forest	24	-0.00017 (-0.2%)	-0.04301 (-9.5%)
garden	30	-0.00097 (-1.2%)	-0.04881 (-11.2%)

Appendix

Table 12: Category-wise change from Tiled Diffusion (

\alpha_{D}=0

) to DepthTile (

\alpha_{D}=1

) for seam-quality metrics. Each cell gives the absolute change followed by the relative change in parentheses.

Figure 6: Artifact suppression in existing-image self-tiling. Each row compares $1\times 2$ repetitions from direct concatenation, DepthTile, and Tiled Diffusion. Black or white dashed boxes mark artifacts introduced by Tiled Diffusion but avoided by DepthTile.

Figure 7: Fine-detail preservation. Yellow boxes identify the compared regions, and the lower-left insets enlarge the same crop for all methods. DepthTile retains local structures closer to the direct-concatenation reference than Tiled Diffusion.

Figure 8: Examples in which stronger content preservation leaves a more visible center seam. DepthTile restricts edits to foreground structures and may therefore retain a slightly stronger discontinuity than Tiled Diffusion.

Figure 9: Examples in which Tiled Diffusion produces the more visible center seam. Aggressive boundary regeneration can increase cross-seam structural or appearance inconsistency, whereas DepthTile preserves a more coherent transition.

Diffusion-Based Image Editing

Diffusion-based image editing changes image content, style, or attributes while aiming to preserve the parts users want to keep.

See all 227 papers

Generative Phomosaic with Structure-Aligned and Personalized Diffusion
Apr 8, 2026Jaeyoung Chung, Hyunjin Son, Kyoung Mu LeeDiffusion-Based Image Generation Conditional Image Generation
Seoul National University, Seoul, South Korea
SWITi: Quantifying and Reducing Tiling Artifacts with Sliding Window Inner Tiling
Jul 21, 2026Federico Carrara, Aman Kukde, Melisande Croft +2Image Reconstruction Fluorescence Microscopy
Fondazione Human Technopole, Milan, Italy · Università Campus Bio-Medico, Rome, Italy
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
Sep 30, 2026Lehan Yang, Daiqing Qi, Wenhao Zhang +9Diffusion Model Alignment Diffusion Transformer
University of Virginia · Michigan State University · Adobe +1

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

Generative Phomosaic with Structure-Aligned and Personalized Diffusion

Jaeyoung Chung, Hyunjin Son, Kyoung Mu Lee

Seoul National University, Seoul, South Korea

Diffusion-Based Image Generation Conditional Image Generation

Open paper AskPDF arXiv

We present the first generative approach to photomosaic creation. Traditional photomosaic methods rely on a large number of tile images and color-based matching, which limits both diversity and structural consistency. Our generative photomosaic framework synthesizes tile images using diffusion-based generation conditioned on reference images. A low-frequency conditioned diffusion mechanism aligns global structure while preserving prompt-driven details. This generative formulation enables photomosaic composition that is both semantically expressive and structurally coherent, effectively overcoming the fundamental limitations of matching-based approaches. By leveraging few-shot personalized diffusion, our model is able to produce user-specific or stylistically consistent tiles without requiring an extensive collection of images.

Abstract

Diffusion-Based Image Editing

Explore similar work

Generative Phomosaic with Structure-Aligned and Personalized Diffusion

SWITi: Quantifying and Reducing Tiling Artifacts with Sliding Window Inner Tiling

PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion