MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

By Donny Y. Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, Jianfei Cai. European Conference on Computer Vision, 2024

571 citations recorded by the source corpus.

We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we build a cost volume representation via plane sweeping, where the cross-view feature similarities stored in the cost volume can provide valuable geometry cues to the estimation of depth. We also learn other Gaussian primitives' parameters jointly with the Gaussian centers while only relying on photometric supervision. We demonstrate the importance of the cost volume representation in learning feed-forward Gaussians via extensive experimental evaluations. On the large-scale RealEstate10K and ACID benchmarks, MVSplat achieves state-of-the-art performance with the fastest feed-forward inference speed (22~fps). More impressively, compared to the latest state-of-the-art method pixelSplat, MVSplat uses $10\times$ fewer parameters and infers more than $2\times$ faster while providing higher appearance and geometry quality as well as better cross-dataset generalization.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fa0c7c850b6298fa49518e42e9f9e492dd4c5541

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ying Shan
2. Jinbo Xing
3. Xiaoyu Li
4. Wangbo Yu
5. Li Yuan
6. Xiangjun Gao
7. Wenbo Hu
8. Tien-Tsin Wong

Citations in the corpus

• Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025, unknown): “We compare our method to two representative works for sparse view reconstruction, Pixel-Splat [6] and MVSplat [8].”
• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis (2024, methodology): “Inspired by the success of 3D-GS [2], recent approaches such as PixelSplat [27] and MVSplat [28] explore training regression-based models to produce 3D Gaussian representations for real-time rendering capabilities.”
• A Survey on 3D Gaussian Splatting (2024, unknown): “To provide a synthesized overview before delving into each direction, Table S1 summarizes their key ideas, representative works (ordered chronologically), advantages, and limitations.”
• Depth Anything 3: Recovering the Visual Space from Any Views (2025, unknown): “Follow-up models extended this paradigm with multi-view inputs [10, 85, 94, 110], video input [19, 59, 94, 121], robust correspondence modeling [48], camera parameter injection [39, 43], large-scale SfM [18], SLAM applications [54], and view synthesis with 3D Gaussians [11, 13, 41, 79, 108, 122].”
• Recent advances in 3D Gaussian splatting (2024, unknown): “[17] follow this idea and propose to input the positional-encoded Gaussian position and timestep t to the MLP which outputs the offsets of the position, rotation, and scaling of 3D Gaussian.”