Research map / 3D vision / Gaussian splatting
Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filtering
Ankit Dhiman, Kunal A Kathare, Pranav Vignesh, LOKESH BOREGOWDA, Venkatesh Babu Radhakrishnan
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 motion-aware smoothing filter to SpeeDe3DGS | SpeeDe3DGS · D-NeRF 4x test | PSNR: 27.83 -> 32.28 | Improved |
| add motion-aware smoothing filter to SpeeDe3DGS | SpeeDe3DGS · D-NeRF 4x test | training time (min): 4.45 -> 6.48 | Hurt |
| add motion-aware filter when rendering at 1/4x resolution | SpeeDe3DGS · D-NeRF zoom-out (1/4x) | PSNR: 28.10 -> 35.87 | Improved |
| add motion-aware filter at training resolution | SpeeDe3DGS · D-NeRF zoom-out (1x) | PSNR: 35.01 -> 35.02 | No clear effect |
| use motion-aware filter instead of static 3D Mip-Splatting filter | SARO-GS + 3D Filter · Plenoptic Video | PSNR: 24.92 -> 6.4 dB improvement | Improved |
| add motion-aware filter to SARO-GS | SARO-GS · Plenoptic Video (train 1x, multi-scale test) | PSNR avg: 29.85 -> 31.01 | Improved |
| add motion-aware filter to SARO-GS at same-scale testing | SARO-GS · Plenoptic Video (single-scale) | SSIM: 0.004 SSIM decrease | Hurt |
| temporal grid size T=100 instead of 25 (ablation) | Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale) | PSNR 4x: 30.58 -> 31.72 | Improved |
| temporal grid size T=100 instead of 150 (ablation) | Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale) | PSNR 4x: 31.11 -> 31.72 | Improved |
| update filter every 100 iterations instead of 300 (ablation) | Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale) | PSNR 4x: 29.34 -> 31.72 | Improved |
| update filter every 100 iterations instead of 200 (ablation) | Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale) | PSNR 4x: 30.64 -> 31.72 | Improved |
| increase kernel bandwidth h_x from 0.1 to 0.3 (ablation) | Motion-aware filter + SpeeDe3DGS · D-NeRF 4x test | PSNR: 32.13 -> 32.28 | No clear effect |
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.
- Grid4D — Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting (NeurIPS 2024) · better on 6 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
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.91)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.90)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.90)
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · similarity 0.89)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.88)
- Robust Multi-Object 4D Generation for In-the-wild Videos (CVPR 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.
