MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
CoRR(2024)
摘要
We propose MVSplat, an efficient feed-forward 3D Gaussian Splatting model
learned from sparse multi-view images. To accurately localize the Gaussian
centers, we propose to build a cost volume representation via plane sweeping in
the 3D space, where the cross-view feature similarities stored in the cost
volume can provide valuable geometry cues to the estimation of depth. We learn
the Gaussian primitives' opacities, covariances, and spherical harmonics
coefficients jointly with the Gaussian centers while only relying on
photometric supervision. We demonstrate the importance of the cost volume
representation in learning feed-forward Gaussian Splatting models via extensive
experimental evaluations. On the large-scale RealEstate10K and ACID benchmarks,
our model achieves state-of-the-art performance with the fastest feed-forward
inference speed (22 fps). Compared to the latest state-of-the-art method
pixelSplat, our model uses 10× fewer parameters and infers more than
2× faster while providing higher appearance and geometry quality as well
as better cross-dataset generalization.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要