Research map / 3D vision / Gaussian splatting
Minute4D: Training High-Fidelity 4D Gaussian Splatting in One Minute
BINJIAN XIE, Chenhui Shi, Pengju Zhang, Yihong Wu
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 Segmentation-Tracking Enhancement (ablation) | Minute4D · DyCheck iPhone | PSNR (dB): 24.60 -> 25.77 | Improved |
| add Segmentation-Tracking Enhancement (ablation) | Minute4D · DyCheck iPhone | SSIM: 0.628 -> 0.717 | Improved |
| add Loss-Guided Density Control (ablation) | Minute4D · DyCheck iPhone | Runtime (s): 397.732 -> 29.224 | Improved |
| add Loss-Guided Density Control (ablation) | Minute4D · DyCheck iPhone | Peak memory (MB): 9406 -> 1088 | Improved |
| add Loss-Guided Density Control (ablation) | Minute4D · DyCheck iPhone | PSNR (dB): 25.74 -> 25.77 | No clear effect |
| use Minute4D instead of Instant4D(Full) | Minute4D · DyCheck iPhone | PSNR (dB): 24.52 -> 25.77 | Improved |
| use Minute4D instead of Instant4D(Full) for training time | Minute4D · DyCheck iPhone | Training runtime (h): 0.12 -> 0.008 | Improved |
| use Minute4D instead of Instant4D | Minute4D · NVIDIA Dynamic Scenes | PSNR (dB): 23.99 -> 24.73 | Improved |
| use Minute4D instead of COLMAP-calibrated DynamicNeRF | Minute4D · NVIDIA Dynamic Scenes | PSNR (dB): 26.10 -> 24.73 | Hurt |
| use Minute4D instead of Instant4D for rendering speed | Minute4D · NVIDIA Dynamic Scenes | Rendering FPS: 822 -> 1218 | 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.
- Instant4D — Instant4D: 4D Gaussian Splatting in Minutes (NeurIPS 2025) · better on 3 of 3 shared results
- D-NeRF — D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021) · 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
- Instant4D: 4D Gaussian Splatting in Minutes (NeurIPS 2025 · similarity 0.94)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.93)
- Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle (CVPR 2024 · similarity 0.90)
- KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences (AAAI 2025 · similarity 0.90)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.90)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.90)
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.
