Research map / 3D vision / Gaussian splatting
ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
Ruijie Zhu, Mulin Yu, Linning Xu, Lihan Jiang, Yixuan Li, Tianzhu Zhang, Jiangmiao Pang, Bo Dai
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use one-hot ID encoding with classification loss instead of learnable Gaussian semantics (ablation) | ObjectGS · LERF-Mask figurines | mIoU: 69.57 -> 88.19 | Improved |
| use one-hot ID encoding instead of object-independent constraints (ablation) | ObjectGS · LERF-Mask figurines | mIoU: 37.48 -> 88.19 | Improved |
| use majority voting instead of probability-based voting for point ID initialization (ablation) | ObjectGS · LERF-Mask figurines | mIoU: 84.46 -> 88.19 | Improved |
| use majority voting instead of correspondence-based voting (ablation) | ObjectGS · LERF-Mask figurines | mIoU: 59.67 -> 88.19 | Improved |
| add semantic loss with weight 0.1 (ablation) | ObjectGS · Replica | PSNR: 40.19 -> 40.26 | Mixed |
| raise semantic loss weight to 1.00 (ablation) | ObjectGS · Replica | PSNR: 40.26 -> 35.43 | Hurt |
| object-aware anchors with discrete semantics versus Gaussian Grouping | Gaussian Grouping · ScanNet++ panoptic (7 scenes) | IoU: 89.82 -> 95.38 | Improved |
| ObjectGS versus Gaga on figurines | LERF-Mask figurines · LERF-Mask figurines | mIoU: 90.7 vs 88.2 | Hurt |
| ObjectGS on many-object ScanNet++ scenes versus Gaussian Grouping | training cost · ScanNet++ 3e8b | training time: 71 min -> 113 min | Hurt |
Later papers that compared with this method
1 later accepted paper reports ObjectGS as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction (CVPR 2026 · better on 0 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Gaussian Grouping — Gaussian Grouping: Segment and Edit Anything in 3D Scenes (ECCV 2024) · better on 7 of 7 shared results
- SAGA — SAGA: Stochastic Whole-Body Grasping with Contact (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 2025 · similarity 0.90)
- Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding (AAAI 2025 · similarity 0.90)
- Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations (NeurIPS 2025 · similarity 0.90)
- Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- 3D Vision-Language Gaussian Splatting (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
