SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914276011147264 |
|---|---|
| author | Ma, Mengjiao Ma, Qi Li, Yue Cheng, Jiahuan Yang, Runyi Ren, Bin Popovic, Nikola Wei, Mingqiang Sebe, Nicu Van Gool, Luc Gevers, Theo Oswald, Martin R. Paudel, Danda Pani |
| author_facet | Ma, Mengjiao Ma, Qi Li, Yue Cheng, Jiahuan Yang, Runyi Ren, Bin Popovic, Nikola Wei, Mingqiang Sebe, Nicu Van Gool, Luc Gevers, Theo Oswald, Martin R. Paudel, Danda Pani |
| contents | 3D Gaussian Splatting (3DGS) serves as a highly performant and efficient encoding of scene geometry, appearance, and semantics. Moreover, grounding language in 3D scenes has proven to be an effective strategy for 3D scene understanding. Current Language Gaussian Splatting line of work fall into three main groups: (i) per-scene optimization-based, (ii) per-scene optimization-free, and (iii) generalizable approach. However, most of them are evaluated only on rendered 2D views of a handful of scenes and viewpoints close to the training views, limiting ability and insight into holistic 3D understanding. To address this gap, we propose the first large-scale benchmark that systematically assesses these three groups of methods directly in 3D space, evaluating on 1060 scenes across three indoor datasets and one outdoor dataset. Benchmark results demonstrate a clear advantage of the generalizable paradigm, particularly in relaxing the scene-specific limitation, enabling fast feed-forward inference on novel scenes, and achieving superior segmentation performance. We further introduce GaussianWorld-49K a carefully curated 3DGS dataset comprising around 49K diverse indoor and outdoor scenes obtained from multiple sources, with which we demonstrate the generalizable approach could harness strong data priors. Our codes, benchmark, and datasets are released at https://scenesplatpp.gaussianworld.ai/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting Ma, Mengjiao Ma, Qi Li, Yue Cheng, Jiahuan Yang, Runyi Ren, Bin Popovic, Nikola Wei, Mingqiang Sebe, Nicu Van Gool, Luc Gevers, Theo Oswald, Martin R. Paudel, Danda Pani Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) serves as a highly performant and efficient encoding of scene geometry, appearance, and semantics. Moreover, grounding language in 3D scenes has proven to be an effective strategy for 3D scene understanding. Current Language Gaussian Splatting line of work fall into three main groups: (i) per-scene optimization-based, (ii) per-scene optimization-free, and (iii) generalizable approach. However, most of them are evaluated only on rendered 2D views of a handful of scenes and viewpoints close to the training views, limiting ability and insight into holistic 3D understanding. To address this gap, we propose the first large-scale benchmark that systematically assesses these three groups of methods directly in 3D space, evaluating on 1060 scenes across three indoor datasets and one outdoor dataset. Benchmark results demonstrate a clear advantage of the generalizable paradigm, particularly in relaxing the scene-specific limitation, enabling fast feed-forward inference on novel scenes, and achieving superior segmentation performance. We further introduce GaussianWorld-49K a carefully curated 3DGS dataset comprising around 49K diverse indoor and outdoor scenes obtained from multiple sources, with which we demonstrate the generalizable approach could harness strong data priors. Our codes, benchmark, and datasets are released at https://scenesplatpp.gaussianworld.ai/. |
| title | SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.08710 |