A curated list of awesome neural radiance fields (NeRF) papers, implementations, and resources.
Awesome Neural Radiance Fields is a curated, community-maintained list of research papers, code implementations, and resources related to Neural Radiance Fields (NeRF). It organizes the expansive literature on NeRF—a technique for creating 3D scene representations from 2D images—into a structured directory, making it easier to explore advancements in faster training, dynamic scenes, generalization, and applications like robotics and editing.
Computer vision researchers, graduate students, and developers working on 3D reconstruction, neural rendering, or novel view synthesis who need a centralized, updated resource for NeRF literature and code.
It saves significant time in literature review by providing a meticulously categorized and crowdsourced index of NeRF research, complete with paper links, code repositories, and bibtex citations, all maintained by the community to ensure comprehensiveness and timeliness.
A curated list of awesome neural radiance fields papers
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
The README organizes hundreds of NeRF papers into detailed categories like Faster Inference and Deformable Scenes, enabling targeted exploration of research areas without manual searching.
It provides links to official codebases in PyTorch, TensorFlow, and JAX, as seen in the Implementations section, saving developers time in locating reliable sources for experimentation.
Papers are categorized by focus such as Generalization, Editing, and Robotics, offering a clear navigation framework that helps users quickly identify relevant advancements.
Open to contributions via pull requests, as noted in the README, ensuring the list stays current with the fast-paced evolution of NeRF technologies.
It functions solely as a link directory without summaries, critiques, or comparisons between papers, forcing users to independently assess paper quality and relevance.
Being community-maintained, entries may lack uniformity, with potential for outdated links, incomplete information, or uneven coverage across sub-domains without centralized vetting.
The list offers no tutorials, best practices, or implementation tips, leaving users to navigate complex codebases and research nuances on their own.