High-fidelity 3D reconstruction of navel oranges using 3D Gaussian splatting
Researchers have developed a new 3D reconstruction framework for navel oranges using 3D Gaussian Splatting and deep-learning-based feature matching. This method overcomes challenges related to the fruit's weakly textured and specular surfaces, providing a more accurate digital model.
Why it matters
This technology improves agricultural quality control and phenotypic analysis by enabling high-fidelity digital documentation of produce.
Scientific Reports ( 2026 ) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in