Japanese Park Captured with 3D Gaussian Splatting

December 26, 2025
|
Updated February 10, 2026
|

2 min read

Japanese park scene featuring a pond, stone lantern, and vibrant autumn foliage.
I’m always excited to see technology used in a unique and artistic manner. In a creative fusion of reality and digital space, developer and artist Masayuki Sugimoto recently showcased a stunning capture of a Japanese park using 3D Gaussian Splatting (3DGS). The project, shared on social media, utilizes a spherical viewing method that allows users to peer into a lush, detailed environment from the inside of a virtual orb. This specific execution highlights the rapid evolution of radiance field technologies, moving beyond static images or traditional mesh-based renders into immersive, fluid environments. By capturing the intricate textures of trees, pathways, and sunlight, the project demonstrates how 3DGS can preserve the “vibe” of a physical location with a level of fidelity and performance that traditional photogrammetry often struggles to achieve.

For professionals in mapping and the earth sciences, 3DGS offers a way to visualize complex environments without the heavy computational load of high-poly meshes. In the context of archaeology and heritage preservation, this “spherical” capture method provides a more intuitive way for the public to interact with site data, turning abstract point clouds into relatable, aesthetic experiences. By focusing on the visual atmosphere as much as the spatial coordinates, Sugimoto demonstrates that lidar-adjacent technologies are becoming powerful tools for both technical documentation and digital art, bridging the gap between raw data collection and human-centric storytelling.

The project serves as a compelling proof of concept for the future of interactive 3D modeling and virtual tourism. As these tools become more accessible, the ability to “teleport” into a precise recreation of a distant park or archaeological site becomes a reality for anyone with a web browser. This specific implementation underscores the versatility of Gaussian splats in handling organic shapes and complex lighting that typically cause artifacts in other scanning methods. For those interested in the technical workflow or the visual results of this Japanese park capture, the full demonstration offers a glimpse into the next generation of spatial media.

Read More: https://80.lv/articles/japanese-park-3dgs-captured-inside-3d-sphere

Written by Adam Clark. Adam has spent the past 13 years exploring the world from above by using drones, satellites, and mapping tools to better understand our landscapes. Connect with him on LinkedIn: Adam Clark

Want to read another recent story: Minecraft and Lidar Recreate University Campus

Get Lidar News in Your Inbox

Weekly updates on lidar tech, geospatial industry news, case studies, and product reviews.

About The Author

Prevu3D webinar
Phoenix Lidar Systems

Recent 3D Modeling Posts

Multispectral Imaging Maps Hidden Stratigraphy

Sixteen wavelengths in an open excavation Researchers from Aarhus University and Moesgaard Museum have developed…

September 8, 2026

Photogrammetry in Games: Rebuilding Gallipoli

Building the terrain from archival records BlackMill Games has released Gallipoli, the latest entry in…

September 1, 2026

Autonomous Navigation Lidar for ESA Moon Mission

Editor’s Note: Autonomous navigation lidar is enabling machines to understand and navigate complex environments without…

July 28, 2026

Lidar Supports Vivid Sydney Projection Mapping

For Vivid Sydney’s Creative Technology After Dark, lidar scanning was used to create accurate digital…

July 7, 2026

Preserving an Icon: Liberty Bell Digital Twin

The Liberty Bell Digital Twin Project recently created the first free, high-resolution public digital twin…

July 2, 2026
The four stages of 3D Gaussian Splatting reconstruction, visualised as a single progression. A sparse point cloud provides the initial spatial skeleton (left); large overlapping Gaussian primitives are seeded from those points and begin to occupy volume (second); the optimiser densifies and refines those primitives, packing them tighter as the form converges (third); finally, alpha-compositing from the correct viewpoint produces a photorealistic render with no visible primitives remaining (right). The primitives never disappear, they simply become coherent. This is not a surface mesh, not a voxel grid, not a neural network at render time. It is millions of learned ellipsoids, each carrying position, shape, rotation, colour and opacity, composited in depth order at real-time frame rates. Image: Mike Devers / Cr8ive Media

Gaussian Splatting and LiDAR: A Practitioner’s Field Guide

3D Gaussian Splatting (3DGS) is one of the most talked-about technologies in reality capture right…

June 23, 2026

Popular Posts

Phoenix Lidar Systems

Get Lidar News in Your Inbox

Weekly updates on lidar tech, geospatial industry news, case studies, and product reviews.

Mach9 Digital Surveyor 2