Research map / 3D vision / Gaussian splatting
A-TDOM: Active TDOM via On-the-Fly 3DGS
Yiwei Xu, Xiang Wang, Yifei Yu, Wentian Gan, Luca Morelli, Giulio Perda, Xin Wang, Zongqian Zhan, Fabio Remondino A
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 Gaussians sampling and integration (instead of default densification) (ablation) | A-TDOM · phantom3 | model size (MB): 990.8 -> 182.5 | Improved |
| add Gaussians sampling and integration (ablation) | A-TDOM · phantom3 | FPS: 0.21 -> 0.59 | Improved |
| add Gaussians sampling and integration (ablation) | A-TDOM · ground | training completion | Improved |
| add adaptive optimization strategies (ablation) | A-TDOM · phantom3 | FPS: 0.41 -> 0.59 | Improved |
| add adaptive optimization strategies (ablation) | A-TDOM · ground | PSNR (dB): 28.46 -> 27.97 | Hurt |
| add key-region determination (ablation) | A-TDOM · phantom3 | PSNR (dB): 31.22 -> 31.81 | Improved |
| add key-region determination (ablation) | A-TDOM · ground | FPS: 0.42 -> 0.46 | Improved |
| start 3DGS only after more than 3 oriented images instead of 3 (add initial stage of 30 images) (ablation) | A-TDOM · phantom3 | PSNR (dB): 30.83 -> 31.81 | Improved |
| use A-TDOM instead of On-the-Fly GS | On-the-Fly GS · UAV image datasets | model size (MB): 524.5 -> 207.4 | Improved |
| use A-TDOM instead of RTG-SLAM (RGB only vs RGB-D) | RTG-SLAM · Replica | FPS: 2.89 -> 4.99 | Improved |
| use A-TDOM instead of AdR-Gaussian (7K) | AdR-Gaussian (7K) · Small-scale scenes | PSNR (dB): 23.92 -> 25.94 | Improved |
| use A-TDOM instead of ContextCapture for TDOM | ContextCapture · UAV TDOM generation | cost time (s): 1515 -> 512 | 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.
- GS-SLAM — GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024) · better on 1 of 1 shared result
- VastGaussian (30K) — VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction (CVPR 2024) · 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
- ActiveGAMER: Active GAussian Mapping through Efficient Rendering (CVPR 2025 · similarity 0.81)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.80)
- RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery (NeurIPS 2026 · similarity 0.80)
- DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments (AAAI 2025 · similarity 0.80)
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 2025 · similarity 0.80)
- Volumetrically Consistent 3D Gaussian Rasterization (CVPR 2025 · similarity 0.80)
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.
