2D Gaussian Splatting for Geometrically Accurate Radiance Fields
3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. However, 3DGS fails to accurately represent surfaces due to the multi-view inconsistent nature of 3D Gaussians. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks. Unlike 3D Gaussians, 2D Gaussians provide view-consistent geometry while modeling surfaces intrinsically. To accurately recover thin surfaces and achieve stable optimization, we introduce a perspective-correct 2D splatting process utilizing ray-splat intersection and rasterization. Additionally, we incorporate depth distortion and normal consistency terms to further enhance the quality of the reconstructions. We demonstrate that our differentiable renderer allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
Code (2)
Tasks
3DGSNovel View SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map
Robots require high-fidelity reconstructions of their environment for effective operation. Such scene representations should be both, geometrically accurate and photorealistic to support downstream tasks. While this can …
3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
Recent advances in radiance field reconstruction, such as 3D Gaussian Splatting (3DGS), have achieved high-quality novel view synthesis and fast rendering by representing scenes with compositions of Gaussian primitives. …
3DGSNovel View SynthesisMixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting
Reconstructing high-fidelity 3D head avatars is crucial in various applications such as virtual reality. The pioneering methods reconstruct realistic head avatars with Neural Radiance Fields (NeRF), which have been limit…
3DGSNeRFCoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization
3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduc…
3DGSNovel View SynthesisSplat the Net: Radiance Fields with Splattable Neural Primitives
Radiance fields have emerged as a predominant representation for modeling 3D scene appearance. Neural formulations such as Neural Radiance Fields provide high expressivity but require costly ray marching for rendering, w…