Optimizing initial noise via backpropagation approximation and spectral parameterization in structured 3D latent diffusion yields higher contextual consistency and prompt alignment in training-free inpainting.
In: CVPR (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
citing papers explorer
-
InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization
Optimizing initial noise via backpropagation approximation and spectral parameterization in structured 3D latent diffusion yields higher contextual consistency and prompt alignment in training-free inpainting.
-
MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.