Image-Space Collage and Packing with Differential Rendering

Zhenyu Wang and Min Lu
Shenzhen University
SIGGRAPH 2025, conference
image

The ‘SIGGRAPH’ example is created using our method: (S) demonstrates the fundamental approach with good shape containment, non-overlap, and uniform distribution; (I) incorporates padding around geometric elements; (G-G) illustrates the smooth transition from axis-based initialization to final filling; (R) showcases collages with stripe blocks; (A) highlights packing within a shape with a downward force; and (P, H) display open packing arrangement with a downward force.

Abstract

Collage and packing techniques are widely used to organize geometric shapes into cohesive visual representations, facilitating the representation of visual features holistically, as seen in image collages and word clouds. Traditional methods often rely on object-space optimization, requiring intricate geometric descriptors and energy functions to handle complex shapes. In this paper, we introduce a versatile image-space collage technique. Leveraging a differentiable renderer, our method effectively optimizes the object layout with image-space losses, bringing the benefit of fixed complexity and easy accommodation of various shapes. Applying a hierarchical resolution strategy in image space, our method efficiently optimizes the collage with fast convergence, large coarse steps first and then small precise steps. The diverse visual expressiveness of our approach is demonstrated through various examples. Experimental results show that our method achieves an order of magnitude speedup performance compared to state-of-the-art techniques.

Animation of the collage process

image image image image image image image image image image image image

How Does it Work

image
mage-space collage and packing framework: starting with initialized 2D geometric items and their transformations, image-space losses are computed between the rasterized image and the target shape of the collage container across a hierarchy of image resolutions. These losses are then used to itera- tively update the transformation parameters, refining the arrangement of the geometric items.

Results

image
A gallery of examples: diverse visual elements (i.e., icons, sketched paths) can be effectively fitted within convex and concave target boundaries.
image
A gallery of examples that texts and graphics are collaged and packed for visually appealing design.

BibTeX

@article{wang2024versatile,
      title={A Versatile Collage Visualization Technique},
      author={Wang, Zhenyu and Lu, Min},
      journal={arXiv preprint arXiv:2406.04008},
      year={2024}
    }