Image-Space Collage and Packing with Differentiable Rendering

TL;DR

This paper presents a novel image-space collage method using differentiable rendering, enabling efficient shape arrangement with fixed complexity and broad shape compatibility, achieving significant speed improvements over existing techniques.

Contribution

The proposed approach introduces an image-space optimization technique with hierarchical resolution, simplifying shape collage creation and accelerating convergence compared to traditional object-space methods.

Findings

Achieves an order-of-magnitude speedup over state-of-the-art methods.

Effectively handles various shapes with fixed complexity.

Demonstrates diverse visual expressiveness in collages.

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 compared to state-of-the-art techniques. The project page is https://szuviz.github.io/pixel-space-collage-technique/.