This paper explores the transition from latent-space diffusion models to pixel-space diffusion generation . We address the "flying pixel" artifact—a common byproduct of Variational Autoencoder (VAE) compression—by performing diffusion directly in the pixel domain. By leveraging semantics-prompted diffusion , our approach ensures high-quality point cloud reconstruction from single-view images. 1. Introduction
Comparison against NYU Depth V2 and KITTI datasets. Pixelpiece3
How high-level semantic cues guide the diffusion process to differentiate between overlapping object boundaries. Pixelpiece3
Traditional monocular depth models like Marigold often suffer from blurry edges and depth artifacts due to the lossy nature of VAEs. Pixelpiece3