Research map / 3D vision / Gaussian splatting
3D Gaussian Splatting from Unposed Spike Stream
Yijia Guo, Tong Hu, Liwen Hu, Lei Ma, Tiejun Huang
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 keyframing to pose optimization (ablation) | Nope-SGS · Tanks and Temples | time per epoch (min): 45.3 -> 3.0 | Improved |
| add keyframing to pose optimization (ablation) | Nope-SGS · Tanks and Temples | PSNR: 29.62 -> 30.184 | Improved |
| use Lsub instead of Lpho for pose optimization (ablation) | Nope-SGS · Tanks and Temples | ATE: 0.007 -> 0.003 | Improved |
| use Lsub instead of Lnbds for pose optimization (ablation) | Nope-SGS · Tanks and Temples | ATE: 0.004 -> 0.003 | Improved |
| add Lnbds to scene optimization (ablation) | Nope-SGS · Tanks and Temples | PSNR: 26.44 -> 30.184 | Improved |
| add Lacc to scene optimization (ablation) | Nope-SGS · Tanks and Temples | PSNR: 29.16 -> 30.184 | Improved |
| add both Lnbds and Lacc to scene optimization (ablation) | Nope-SGS · Tanks and Temples | PSNR: 22.42 -> 30.184 | Improved |
| Nope-SGS versus best baseline on novel view synthesis | Nope-SGS · Tanks and Temples | PSNR: +7.4dB PSNR, 30% higher SSIM, 64% lower LPIPS | Improved |
| estimate poses jointly with Nope-SGS instead of COLMAP or VGGT | SpikeGS · Tanks and Temples | ATE: 0.012 -> 0.003 | Improved |
| Nope-SGS reconstruction speed versus prior spike-based methods | Nope-SGS · spike-based 3D reconstruction | reconstruction time: 3x faster | Improved |
| Nope-SGS versus pose-free and spike methods on depth | Nope-SGS · depth estimation (pseudo GT) | AbsRel: 0.61 -> 0.31 | 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.
- SpikeGS — SpikeGS: Reconstruct 3D Scene Captured by a Fast-Moving Bio-Inspired Camera (AAAI 2025) · better on 1 of 1 shared result
- USP-Gaussian — USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting (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
- SpikeGS: Reconstruct 3D Scene Captured by a Fast-Moving Bio-Inspired Camera (AAAI 2025 · similarity 0.95)
- USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting (CVPR 2025 · similarity 0.93)
- KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences (AAAI 2025 · similarity 0.90)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.89)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 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.
