paper-with-me

Papers

NeRF-Insert: 3D Local Editing with Multimodal Control Signals

2024-04-30 · Benet Oriol Sabat, Alessandro Achille, Matthew Trager, Stefano Soatto

We propose NeRF-Insert, a NeRF editing framework that allows users to make high-quality local edits with a flexible level of control. Unlike previous work that relied on image-to-image models, we cast scene editing as an in-painting problem, which encourages the global structure of the scene to be preserved. Moreover, while most existing methods use only textual prompts to condition edits, our framework accepts a combination of inputs of different modalities as reference. More precisely, a user may provide a combination of textual and visual inputs including images, CAD models, and binary image masks for specifying a 3D region. We use generic image generation models to in-paint the scene from multiple viewpoints, and lift the local edits to a 3D-consistent NeRF edit. Compared to previous methods, our results show better visual quality and also maintain stronger consistency with the original NeRF.

📄 PDF Abstract BibTeX arXiv:2404.19204

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationNeRF

Similar Papers 제목 키워드 기반

Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fields

2023-07-24 · Shangzhan Zhang, Sida Peng, Yinji ShenTu, Qing Shuai 외

Recently, the editing of neural radiance fields (NeRFs) has gained considerable attention, but most prior works focus on static scenes while research on the appearance editing of dynamic scenes is relatively lacking. In …

NeRF

LC-NeRF: Local Controllable Face Generation in Neural Randiance Field

2023-02-19 · Wenyang Zhou, Lu Yuan, ShuYu Chen, Lin Gao 외

3D face generation has achieved high visual quality and 3D consistency thanks to the development of neural radiance fields (NeRF). Recently, to generate and edit 3D faces with NeRF representation, some methods are propos…

Face GenerationNeRF

Insert Anything: Image Insertion via In-Context Editing in DiT

2025-04-21 · Wensong Song, Hong Jiang, Zongxing Yang, Ruijie Quan 외

This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Ins…

Virtual Try-on

Towards a Training Free Approach for 3D Scene Editing

2024-12-17 · Vivek Madhavaram, Shivangana Rawat, Chaitanya Devaguptapu, Charu Sharma 외

Text driven diffusion models have shown remarkable capabilities in editing images. However, when editing 3D scenes, existing works mostly rely on training a NeRF for 3D editing. Recent NeRF editing methods leverages edit…

3D scene EditingNeRF

Local 3D Editing via 3D Distillation of CLIP Knowledge

2023-06-21 · CVPR 2023 1 · Junha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee 외

3D content manipulation is an important computer vision task with many real-world applications (e.g., product design, cartoon generation, and 3D Avatar editing). Recently proposed 3D GANs can generate diverse photorealis…

NeRF