Nicu Sebe, Ender Konukoglu, Luc Gool, Martin Oswald, Bin Ren, Danda Paudel, Nikola Popovic, St Kliment Ohridski, Yue Li, Qi Ma, Runyi Yang, Theo Gevers, and 2 more
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Figure 1. We present the 3DGS indoor dataset SceneSplat-7K which includes 7K scenes generated from ARKitScenes [1], Replica [46], ScanNet [5], ScanNet++ [57], Hypersim[43], 3RScan [49], and Matterport3D [2]. Leveraging this high-quality dataset, we propose SceneSplat, the first model to predict open-vocabulary language features for millions of 3D Gaussians in a single forward pass.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.18052")
get_code_for_paper("2503.18052")
have("2503.18052")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2503.18052.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2503.18052)
Connect an agent — have() is free.