Research map / 3D vision / Gaussian splatting
Splat-based 3D Scene Reconstruction with Extreme Motion-blur
Hyeonjoong Jang, Dongyoung Choi, Donggun Kim, Woohyun Kang, Min H. Kim
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 |
|---|---|---|---|
| fix the scale of the Gaussians (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | PSNR: 21.656 -> 26.681 | Improved |
| fix the scale of the Gaussians (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | ATE: 0.155 -> 0.103 | Improved |
| fix the scale of the Gaussians (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | RPE (rot): 1.488 -> 0.195 | Improved |
| add global pose and geometry refinement (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | PSNR: 22.223 -> 26.681 | Improved |
| add global pose and geometry refinement (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | Depth RMSE: 0.027 -> 0.010 | Improved |
| add global pose and geometry refinement (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | ATE: 0.123 -> 0.103 | Improved |
| add global pose and geometry refinement (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | RPE (trans): 0.007 -> 0.012 | Hurt |
| add global pose and geometry refinement (ablation) | Gaussian refinement pipeline · Synthetic RGB-D ablation | RPE (rot): 0.047 -> 0.195 | Hurt |
| add depth loss in deblurring stage (ablation) | deblurring pipeline · Synthetic RGB-D ablation | PSNR: 25.518 -> 26.681 | Improved |
| add depth loss in deblurring stage (ablation) | deblurring pipeline · Synthetic RGB-D ablation | SSIM: 0.807 -> 0.838 | Improved |
| add depth loss in deblurring stage (ablation) | deblurring pipeline · Synthetic RGB-D ablation | LPIPS: 0.170 -> 0.172 | No clear effect |
| use Ours instead of MonoGS for deblurring from novel views | Ours · Synthetic RGB-D deblurring, Bedroom | PSNR: 23.728 -> 26.745 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 3 of 6 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
- BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting (CVPR 2025 · similarity 0.90)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024 · similarity 0.89)
- KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences (AAAI 2025 · similarity 0.89)
- Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting (ICLR 2025 · similarity 0.89)
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.
