CVAug 17, 2023

Watch Your Steps: Local Image and Scene Editing by Text Instructions

arXiv:2308.08947v155 citationsh-index: 41
Originality Incremental advance
AI Analysis

This addresses the challenge of precise, text-guided editing for images and neural radiance fields, though it is incremental as it builds on existing diffusion models.

The paper tackles the problem of localizing edit regions from text instructions in images and 3D scenes, achieving state-of-the-art performance by using relevance maps derived from InstructPix2Pix discrepancies to guide modifications.

Denoising diffusion models have enabled high-quality image generation and editing. We present a method to localize the desired edit region implicit in a text instruction. We leverage InstructPix2Pix (IP2P) and identify the discrepancy between IP2P predictions with and without the instruction. This discrepancy is referred to as the relevance map. The relevance map conveys the importance of changing each pixel to achieve the edits, and is used to to guide the modifications. This guidance ensures that the irrelevant pixels remain unchanged. Relevance maps are further used to enhance the quality of text-guided editing of 3D scenes in the form of neural radiance fields. A field is trained on relevance maps of training views, denoted as the relevance field, defining the 3D region within which modifications should be made. We perform iterative updates on the training views guided by rendered relevance maps from the relevance field. Our method achieves state-of-the-art performance on both image and NeRF editing tasks. Project page: https://ashmrz.github.io/WatchYourSteps/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes