Depth guided method improves seamless image self-tiling quality
DepthTile: Depth-Guided Existing-Image Self-Tiling with Input-Side Tileability Assessment
Computer Vision and Pattern Recognition
Summary
Making an image repeat perfectly as a tile without obvious seams is tricky because changes can distort important parts. The authors introduce DepthTile, which uses depth information from a single image to know which areas to protect and which can be edited. This helps keep important objects sharp while making the image tile seamlessly. They also created a quick way to predict if tiling will work well for a given image.
What this means in practice
- •For graphic designers: Generate seamless repeating tiles from existing images while preserving important content for digital backgrounds and textures.
- •For game developers: Create tiled textures that maintain important visual details and reduce distortion for 3D environments using depth-aware editing.
Authors
Rui Wang, Xi Chen, Hui Dai, Piaopiao Yu, Yixue Hao, Long Hu, Min Chen
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.