Abstract
Feed-forward 3D Gaussian Splatting (3DGS) increasingly aggregates multi-view evidence with heavy learned 3D networks. We propose LoCoSplat (Local-Context Splatting), motivated by the observation that a Gaussian is a local primitive: once depth is predicted, what the 3D stage must add (scale, rotation, opacity) depends on the point cloud around each anchor, and a fixed local average of that neighbourhood is enough to supply it, no heavy network required. LoCoSplat realises exactly this average: it splats a 16-d linear projection of the point features into a fine and a coarse grid and reads both back at each anchor with a 0.14M-parameter pointwise MLP; with no learned 3D network and no dynamic sparse computation, its whole encoder runs as one fp16 CUDA graph. On RealEstate10K, LoCoSplat outperforms every prior feed-forward method on PSNR, SSIM, and LPIPS at 6, 12, and 24 views, with a margin that widens as views densify (+3.3 PSNR over VolSplat, the prior voxel-aligned state of the art, at 24 views) and grows further under zero-shot transfer to ACID and fine-tuning on ScanNet. It reconstructs a 6-view scene in 33 ms on one NVIDIA RTX PRO 6000 GPU, the fastest of seven feed-forward methods and $4.2\times$ faster than the previous state of the art, trains $2.7\times$ faster ($5.9\times$ at 24 views), and uses $6.7\times$ less inference memory.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wang, S., He, J., Sun, Y., Chen, D., Lu, S., & Zhu, B. (2026). LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning. https://omanscience.com/en/articles/locosplat-real-time-feed-forward-3d-gaussian-splatting-with-minimal-3d-reasoning
MLA 9
Wang, Sinan, et al. "LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning." https://omanscience.com/en/articles/locosplat-real-time-feed-forward-3d-gaussian-splatting-with-minimal-3d-reasoning.
Chicago (author–date)
Wang, Sinan, Jinjin He, Yuchen Sun, Duowen Chen, Shenyifan Lu, and Bo Zhu. 2026. "LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning." https://omanscience.com/en/articles/locosplat-real-time-feed-forward-3d-gaussian-splatting-with-minimal-3d-reasoning.
Harvard
Wang, S., He, J., Sun, Y., Chen, D., Lu, S. and Zhu, B. (2026) 'LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning', Available at: https://omanscience.com/en/articles/locosplat-real-time-feed-forward-3d-gaussian-splatting-with-minimal-3d-reasoning.
Vancouver
Wang S, He J, Sun Y, Chen D, Lu S, Zhu B. LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning. https://omanscience.com/en/articles/locosplat-real-time-feed-forward-3d-gaussian-splatting-with-minimal-3d-reasoning
IEEE
S. Wang, J. He, Y. Sun, D. Chen, S. Lu, and B. Zhu, "LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning," https://omanscience.com/en/articles/locosplat-real-time-feed-forward-3d-gaussian-splatting-with-minimal-3d-reasoning.