Research map / 3D vision / Gaussian splatting
FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation
Qijian Tian, Xin Tan, Jiayu Ying, Xuhong Wang, Yuan Xie, Lizhuang Ma
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 |
|---|---|---|---|
| add sparse semantic Gaussians (DGLE) instead of per-Gaussian embeddings (voxel) (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | storage (MB): 396.7 -> 18.04 | Improved |
| add sparse semantic Gaussians (DGLE) instead of per-Gaussian embeddings (voxel) (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | mIoU: 47.83 -> 46.87 | Mixed |
| add sparse semantic Gaussians instead of pixel-aligned embeddings (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | PSNR: 26.13 -> 26.66 | Improved |
| add instance-guided contrastive learning (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | mIoU: 40.22 -> 46.87 | Improved |
| add novel-view distillation (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | PSNR: 24.77 -> 26.66 | Improved |
| add novel-view distillation (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | mIoU: 46.49 -> 46.87 | Improved |
| add geometric distillation from VGGT (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | mIoU: 18.56 -> 46.87 | Improved |
| add geometric distillation from VGGT (ablation) | FLEG · ScanNet++ ablation (avg 2-16 views) | PSNR: 14.38 -> 26.66 | Improved |
| increase semantic voxel size up to 0.016 (ablation) | FLEG · ScanNet++ | mIoU | No clear effect |
| increase semantic voxel size beyond 0.016 (ablation) | FLEG · ScanNet++ | mIoU | Hurt |
| FLEG vs Uni3R on 2 input views | FLEG · ScanNet++ (2 views) | mIoU: 39.54 -> 46.61 | Improved |
| FLEG vs AnySplat camera pose, 2 views | FLEG · ScanNet++ pose | AUC@30: 0.3600 -> 0.4407 | Improved |
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.
- Uni3R — Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images (CVPR 2026) · better on 5 of 5 shared results
- VGGT — VGGT: Visual Geometry Grounded Transformer (CVPR 2025) · 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)
- Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding (CVPR 2024 · similarity 0.89)
- Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration (CVPR 2025 · similarity 0.88)
- 3D Vision-Language Gaussian Splatting (ICLR 2025 · similarity 0.88)
- SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene Understanding (AAAI 2025 · similarity 0.87)
- Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression (CVPR 2025 · similarity 0.87)
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.
