This repository is a curated list of research papers focused on Radiance Field-based 3D editing techniques. It serves as a comprehensive resource for researchers and practitioners in computer vision and graphics looking to explore advancements in manipulating and editing 3D scenes represented by Neural Radiance Fields (NeRFs) and related technologies like 3D Gaussian Splatting. The primary benefit is providing a structured overview of seminal works, surveys, and recent developments in this rapidly evolving field.

How It Works

The repository functions as a dynamic bibliography, categorizing papers by year and conference, and often linking to project pages or code repositories. It aims to track the evolution of NeRF editing, from foundational concepts to state-of-the-art methods that leverage diffusion models, semantic understanding, and various geometric representations for manipulation tasks. The curation process encourages community contributions to maintain up-to-date coverage.

Quick Start & Requirements

This repository is a list of papers and does not have direct installation or execution requirements. Links to associated project pages and code are provided for individual papers.

Highlighted Details

• Extensive coverage of papers from major conferences like CVPR, ICCV, ECCV, NeurIPS, SIGGRAPH, and ICLR.
• Categorization includes seminal papers, surveys, and recent research, updated as of March 2025.
• Focuses on diverse editing capabilities such as text-guided manipulation, object removal, stylization, and relighting.
• Includes papers on both NeRF and the increasingly popular 3D Gaussian Splatting techniques.

Maintenance & Community

The list is actively maintained, with the latest update noted as March 31, 2025. Users are encouraged to contribute missing papers via Issues or Pull Requests.

Licensing & Compatibility

This project is licensed under the MIT License, allowing for broad use and compatibility.

Limitations & Caveats

The README explicitly notes that the acceptance status of papers might not be up-to-date, and users should verify this information independently.