PixelHacker: Diffusion‑Based Image Inpainting with Latent Class Guidance Beats SOTA

PixelHacker introduces a latent class guidance (LCG) paradigm that injects foreground and background embeddings into a diffusion model, training on 14 million image‑mask pairs and achieving state‑of‑the‑art structural and semantic consistency across Places2, CelebA‑HQ and FFHQ benchmarks.

PixelHackerSOTAcomputer vision

0 likes · 16 min read

PixelHacker: Diffusion‑Based Image Inpainting with Latent Class Guidance Beats SOTA