3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
Authors:
- 10 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21360-21369
Abstract
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. However, 3D Gaussians present several limitations for scene reconstruction. Accurately capturing hard edges is challenging without significantly increasing the number of Gaussians, creating a large memory footprint. Moreover, they struggle to represent flat surfaces, as they are diffused in space. Without hand-crafted regularizers, they tend to disperse irregularly around the actual surface. To circumvent these issues, we introduce a novel method, named 3D Convex Splatting (3DCS), which leverages 3D smooth convexes as primitives for modeling geometrically-meaningful radiance fields from multi-view images. Smooth convex shapes offer greater flexibility than Gaussians, allowing for a better representation of 3D scenes with hard edges and dense volumes using fewer primitives. Powered by our efficient CUDA-based rasterizer, 3DCS achieves superior performance over 3DGS on benchmarks such as MipNeRF360, Tanks and Temples, and Deep Blending. Specifically, our method attains an improvement of up to 0.81 in PSNR and 0.026 in LPIPS compared to 3DGS while maintaining high rendering speeds and reducing the number of required primitives. Our results highlight the potential of 3D Convex Splatting to become the new standard for high-quality scene reconstruction and novel view synthesis. The project page is https://convexsplatting.github.ioKeywords
All Related Versions
This publication has 49 references indexed in Scilit:
- TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks2024
- Differentiable Convex Polyhedra Optimization from Multi-view Images2024
- TensoRF: Tensorial Radiance Fields2022
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- OpenDR: An Approximate Differentiable Renderer2014
- Sphere Packings, Lattices and Groups1999
- Optical models for direct volume renderingIEEE Transactions on Visualization and Computer Graphics, 1995
- The sphere packing problemJournal of Computational and Applied Mathematics, 1992
- What can be seen in three dimensions with an uncalibrated stereo rig?1992
- An efficient algorith for determining the convex hull of a finite planar setInformation Processing Letters, 1972