Hong, Ling Yang, Wentao Zhang, Bin Cui, Jingwei Liu, Zhilong Zhang, Zhilin Huang, Zheming Cai
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a pixel-wise or feature-wise constraint along spatial axes. However, such point-based reconstruction may fail to make each predicted pixel/feature fully preserve its neighborhood context, impairing diffusion-based image synthesis. As a powerful source of automatic supervisory signal, context has been well studied for learning representations. Inspired by this, we for the first time propose CONPREDIFF to improve diffusion-based image synthesis with context prediction. We explicitly reinforce each point to predict its neighborhood context (i.e., multi-stride features/tokens/pixels) with a context decoder at the end of diffusion denoising blocks in training stage, and remove the decoder for inference. In this way, each point can better reconstruct itself by preserving its semantic connections with neighborhood context. This new paradigm of CONPREDIFF can generalize to arbitrary discrete and continuous diffusion backbones without introducing extra parameters in sampling procedure. Extensive experiments are conducted on unconditional image generation, text-to-image generation and image inpainting tasks. Our CON-PREDIFF consistently outperforms previous methods and achieves a new SOTA text-to-image generation results on MS-COCO, with a zero-shot FID score of 6.21.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2401.02015")
get_code_for_paper("2401.02015")
have("2401.02015")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2401.02015.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2401.02015)
Connect an agent — have() is free.