Research map / 3D vision / Gaussian splatting
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Fangfu Liu, Hao Li, Jiawei Chi, Hanyang Wang, Minghui Yang, Fudong Wang, Yueqi Duan
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 progressive training (ablation) | LangScene-X · ScanNet (scene0085) | mIoU: 44.25 -> 51.68 | Improved |
| add progressive training (ablation) | LangScene-X · LERF (Teatime) | mIoU: 39.04 -> 45.07 | Improved |
| add language quantized compressor (ablation) | LangScene-X · ScanNet (scene0085) | mIoU: 44.59 -> 51.68 | Improved |
| add language quantized compressor (ablation) | LangScene-X · LERF (Teatime) | mIoU: 41.56 -> 45.07 | Improved |
| add L_s2d loss (ablation) | LangScene-X · ScanNet (scene0085) | mIoU: 40.05 -> 51.68 | Improved |
| add L_s2d loss (ablation) | LangScene-X · LERF (Teatime) | mIoU: 36.26 -> 45.07 | Improved |
| progressive training of TriMap video diffusion (ablation) | TriMap video diffusion · two-view frame matching | matched points | Improved |
| LQC vs regular autoencoder (ablation) | language feature compression · COCO training | L2 loss: 1e^{-3} to 1e^{-4} | Improved |
| replace best prior method with LangScene-X | LERF-OVS · LERF-OVS | mIoU: 10.58% | Improved |
| replace best prior method with LangScene-X | ScanNet · ScanNet | mIoU: 14.92% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- LangSplat — LangSplat: 3D Language Gaussian Splatting (CVPR 2024) · better on 4 of 4 shared results
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
- LangSplat: 3D Language Gaussian Splatting (CVPR 2024 · similarity 0.90)
- Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding (CVPR 2024 · similarity 0.89)
- SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene Understanding (AAAI 2025 · similarity 0.89)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.88)
- From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs (ICML 2025 · similarity 0.88)
- 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.
