3D Gaussian Splatting for Real-Time Radiance Field Rendering

🤖 Plain-English Summary

Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropi...

🔑 Key Findings

• However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality.
• For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates.
• We introduce three key elements that allow us to achieve advanced visual quality while maintaining competitive training times and importantly allow high-quality real-time (≥ 30 fps) novel-view synthesis at 1080p resolution.

🔗 Related Resources