Spaces:
Running on Zero
Download README.md from hugging-apps/gaussianrenderformer: direct link, hf CLI and curl.
- Browser
- Download file 3.01 kB
-
https://huggingface.co/spaces/hugging-apps/gaussianrenderformer/resolve/main/README.md
- Command line
-
hf download hf://spaces/hugging-apps/gaussianrenderformer/README.md
-
curl -L -o README.md https://huggingface.co/spaces/hugging-apps/gaussianrenderformer/resolve/main/README.md
A newer version of the Gradio SDK is available: 6.32.0
title: GaussianRenderFormer
emoji: ✨
colorFrom: pink
colorTo: blue
sdk: gradio
sdk_version: 6.31.0
app_file: app.py
python_version: '3.12'
short_description: Transformer-based rendering of 3D Gaussian splats
startup_duration_timeout: 30m
GaussianRenderFormer
Transformer-based rendering of 3D Gaussian splats — pick a Gaussian Splatting scene, point an orbit camera at it, and a transformer renders the view. No rasterizer, no per-scene optimization: each Gaussian's 14 parameters become one scene token, a view decoder cross-attends over 4-px image patches, and a DPT head produces the image.
- Paper: arXiv:2611.05593 — Valencia Levy & Benaim, 2026
- Code: github.com/SVLwoof/gaussianformer (MIT)
- Checkpoint: shahafvl/gaussianformer (MIT)
What you can do here
- Example scenes — three synthetic splats authored for this demo (a faceted
gem, a glazed vase, a ringed planet, each ≤ 20k Gaussians) rendered through
the exact PLY →
read_ply→normalizepath the model uses in production. - Your own splat — upload a 3DGS
.ply(raw optimizer fields: log scales, wxyz quaternions, SH colors, opacity logits). Tell the app the file's up axis and it centers, re-orients and scales the object into the model's frame. Splats larger than 20k Gaussians are pruned by an importance score; the model was trained on ~20k-Gaussian objects and denser inputs lose quality.
The camera orbits the object's center: azimuth, elevation and distance (the model was trained at distances 1.15–2.45, 45° FOV, 512 px).
Deviations from the reference pipeline
The reference load_ply prunes with gsplat-projected radii and then fine-tunes
the kept Gaussians against the full splat for ~1500 iterations. A CUDA
rasterizer with a JIT build does not fit this demo's runtime, so pruning here
uses an analytic approximation of the same importance score (opacity ×
projected area estimated from pinhole geometry, × scale^0.1) without the
fine-tune. Per the model card, large pruned splats can "lose coverage and turn
dark" without the fine-tune — the bundled examples are ≤ 20k Gaussians and so
are never pruned.
Example scenes & licensing
The three example scenes are original synthetic splats generated procedurally for this demo (no captured data), so they carry no third-party license restrictions. The model was trained on Objaverse_Splats, whose objects each keep their creator's license — that is why the demo does not bundle any of the paper's evaluation scenes.
Limitations (from the model card)
Trained on isolated single objects centered, Y-up and scaled into [-0.45, 0.45]³, at 512 px and 45° FOV; denser inputs lose quality; colors are view-independent (only each Gaussian's DC color is used); fine detail renders softer than a rasterizer.