Model Releases
Deep sprite-based image models: An analysis
arXiv:2604.19480v1 Announce Type: new Abstract: While foundation models drive steady progress in image segmentation and diffusion algorithms compose always more realistic images, the seemingly simple
arXiv:2604.19480v1 Announce Type: new Abstract: While foundation models drive steady progress in image segmentation and diffusion algorithms compose always more realistic images, the seemingly simple problem of identifying recurrent patterns in a collection of images remains very much open. In this paper, we focus on sprite-based image decomposition models, which have shown some promise for clustering and image decomposition and are appealing because of their high interpretability. These models come in different flavors, need to be tailored to specific datasets, and struggle to scale to images with many objects. We dive into the details of their design, identify their core components, and perform an extensive analysis on clustering benchmarks. We leverage this analysis to propose a deep sprite-based image decomposition method that performs on par with state-of-the-art unsupervised class-aware image segmentation methods on the standard CLEVR benchmark, scales linearly with the number of objects, identifies explicitly object categories, and fully models images in an easily interpretable way.
Related
- FineEdit: Fine-Grained Image Edit with Bounding Box Guidance
- FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
- Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
- When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
- Generative Refinement Networks for Visual Synthesis
Source: arXiv cs.CV | 2026-04-22