|
Download README.md from Modularcomputing/Polymorphic: direct link, hf CLI and curl.
- Browser
- Download file 3.23 kB
-
https://huggingface.co/Modularcomputing/Polymorphic/resolve/main/README.md
- Command line
-
hf download hf://Modularcomputing/Polymorphic/README.md
-
curl -L -o README.md https://huggingface.co/Modularcomputing/Polymorphic/resolve/main/README.md
3.23 kB
| # Polymorphic | |
| **Compute-efficient video-to-3D research by Modular Computing.** | |
| This repository contains the Polymorphic video-to-3D experiments and releases. The current public experiment combines **AnySplat** for scene/camera initialization with **Fourier Splatting** for per-scene optimization and novel-view synthesis. | |
| > **Important:** This is an experimental reconstruction pipeline, not a feed-forward model that instantly converts any video into a finished asset. Each new scene requires optimization. The released representation is a renderable splat scene; mesh/GLB conversion is not included as a validated workflow. | |
| ## Featured experiment: Fourier Splatting | |
| [**Open the full experiment model card and run instructions β**](experiments/fourier-splatting/README.md) | |
| The experiment directory contains: | |
| - Runnable preparation and evaluation scripts | |
| - Apartment and kitchen scene checkpoints | |
| - PLY exports at Fourier frequency levels K=1β6 | |
| - Per-scene metrics, experiment report, and third-party license notices | |
| ### Held-out novel-view results | |
| Metrics are from two indoor scenes, using the same VGG LPIPS implementation for both methods. Higher PSNR/SSIM is better; lower LPIPS is better. | |
| | Scene | Method | PSNR β | SSIM β | VGG LPIPS β | Primitives | | |
| |---|---|---:|---:|---:|---:| | |
| | Apartment | AnySplat baseline | 19.1235 | 0.6612 | 0.3154 | 1,858,896 | | |
| | Apartment | Fourier Splatting K=6 | 20.3469 | 0.7041 | 0.3173 | 99,483 | | |
| | Kitchen | AnySplat baseline | 21.6155 | 0.6660 | 0.2678 | 1,983,229 | | |
| | Kitchen | Fourier Splatting K=6 | 25.3078 | 0.8212 | 0.2586 | 120,000 | | |
| Across these two scenes, Fourier Splatting used approximately **16.5β18.7Γ fewer primitives** than the AnySplat baselines. Apartment LPIPS was slightly worse, so the results do not indicate uniform improvement. This is a small exploratory evaluation, not a generalization or state-of-the-art claim. | |
| ## Quick links | |
| - [Fourier Splatting model card and instructions](experiments/fourier-splatting/README.md) | |
| - [Experiment report](experiments/fourier-splatting/FOURIER_SPLATTING_REPORT.md) | |
| - [Metrics JSON](experiments/fourier-splatting/fourier_results.json) | |
| - [Generic video-frame preparation script](experiments/fourier-splatting/scripts/make_fourier_scene_generic.py) | |
| - [Apartment PLY, K=6](experiments/fourier-splatting/models/apartment/lod/fourier_k6.ply) | |
| - [Kitchen PLY, K=6](experiments/fourier-splatting/models/kitchen/lod/fourier_k6.ply) | |
| ## Reproducing the experiment | |
| Start with the [experiment README](experiments/fourier-splatting/README.md), which documents dependencies, frame extraction, scene preparation, optimization, rendering, results, and known limitations. The research run was conducted on an NVIDIA H100 80 GB with PyTorch/CUDA 12.9 at 448Γ448 resolution. The complete workflow has **not yet been validated from a clean environment**, and dependency compatibility may require adjustments. | |
| ## Licensing | |
| This is a research release that incorporates upstream AnySplat and Fourier Splatting code. Their respective license terms apply; see the license notices in the experiment directory. In particular, review Fourier Splatting's non-commercial research/evaluation terms before any commercial use. | |