Front3D-only card after Waymo split

README.md

@@ -1,108 +1,50 @@
 ---
-license: apache-2.0
+license: other
+license_name: 3d-front-license-nc
+license_link: https://3dfront.github.io/
+library_name: worldflow3d
 tags:
-  - 3d-generation
-  - diffusion
+  - 3d-scene-generation
   - flow-matching
-  - voxel
-  - scene-generation
-  - autonomous-driving
-  - indoor-scenes
-datasets:
-  - waymo-open-dataset
-  - 3D-FRONT
+  - diffusers
+  - indoor
+  - front3d
+  - non-commercial
 ---
 
-# WorldFlow3D
+# WorldFlow3D — Front3D (indoor) models
 
-Hierarchical, map/layout-conditioned **3D scene generation** via chunked flow
-matching. This repo holds the released model **cascade** (coarse → refinement) for
-both outdoor (Waymo, map-conditioned) and indoor (3D-FRONT, layout-conditioned)
-scenes, packaged in the [diffusers](https://github.com/huggingface/diffusers) style.
+Layout-conditioned 3D indoor-scene generation (3D-FRONT), as a coarse → color
+refinement flow-matching cascade. Use with the
+[`worldflow3d`](https://github.com/princeton-computational-imaging/WorldFlow3D)
+package (`pip install worldflow3d`).
 
-- **Code:** <https://github.com/princeton-computational-imaging/WorldFlow3D>
-- **License:** Apache-2.0 (code & weights). **Training data** (Waymo Open Dataset,
-  3D-FRONT) carries its own terms — see *Training data & licensing* below.
+> **License.** These models are trained on the **3D-FRONT** dataset and are
+> released for **non-commercial / research use** under the 3D-FRONT dataset
+> terms. The `worldflow3d` *code* is Apache-2.0, but that license does not grant
+> rights to these 3D-FRONT-derived weights. See the 3D-FRONT dataset terms.
 
-## Repository layout (one repo = the whole cascade)
+The **Waymo** (outdoor) models are trained on the Waymo Open Dataset and live in
+a separate repo, [`pci-lab/worldflow3d-waymo`](https://huggingface.co/pci-lab/worldflow3d-waymo),
+under the Waymo Dataset License (non-commercial).
 
-Each stage is a self-contained diffusers layout in its own **subfolder**. The model
-*code* ships in the `worldflow3d` package, so the subfolders hold only weights + config:
+## Cascade stages
 
-```
-waymo-coarse/     coarse outdoor geometry (map-conditioned), 0.4 m voxels
-waymo-refine/     source-flow refinement -> 0.2 m voxels
-front3d-coarse/   coarse indoor geometry
-front3d-color/    source-flow + color refinement (unet in=4)
-```
-
-The four `unet/` folders are four distinct trained models, not copies.
+| Subfolder | Role |
+|-----------|------|
+| `front3d-coarse` | coarse layout-conditioned generation (direct-diffusion) |
+| `front3d-color` | source-flow + color refinement (UNet in=4, color mesh sidecar) |
 
 ## Usage
 
-```bash
-pip install worldflow3d   # see the GitHub repo for source install
-```
-
 ```python
-import numpy as np
 from worldflow3d import WorldFlow3DPipeline
-from worldflow3d.pipeline.datatypes import LayoutContext
-from worldflow3d.conditioning.waymo import load_waymo_map_json
-from worldflow3d.recon import save_mesh
-
-# Load the Waymo coarse -> refine cascade straight from this repo.
-pipe = WorldFlow3DPipeline.from_hub(
-    "pci-lab/worldflow3d", stage="waymo-coarse", refinement_stages=["waymo-refine"],
-    device="cuda",
-)
-
-map_json = load_waymo_map_json("102062", map_dir="waymo_maps", data_root="waymo_scenes")
-transform = np.load("waymo_scenes/coord_transforms/udf_voxel_0.4/segment-102062_training.npy",
-                    allow_pickle=True).item()
-ctx = LayoutContext("waymo", "102062", map_json, transform_data=transform)
-
-result = pipe(layout_context=ctx, cfg_scale=1.5, sampling_steps=30,
-              refine=True, refine_sampling_steps=30, use_uniform_chunking=True,
-              smaller_map=True, fraction=0.12)
-save_mesh(result.voxels.cpu(), result.voxel_size, "scene.ply")
-```
-
-Indoor (3D-FRONT), layout-conditioned coarse → color refinement:
 
-```python
 pipe = WorldFlow3DPipeline.from_hub(
-    "pci-lab/worldflow3d", stage="front3d-coarse", refinement_stages=["front3d-color"],
-    device="cuda",
+    "pci-lab/worldflow3d", stage="front3d-coarse",
+    refinement_stages=["front3d-color"], device="cuda",
 )
 ```
 
-> **Loading note.** Use `WorldFlow3DPipeline.from_hub(...)` (this package). The bare
-> `diffusers.DiffusionPipeline.from_pretrained(repo, trust_remote_code=True)` one-liner
-> does **not** work here: diffusers reads `model_index.json` only from a repo *root*,
-> never a subfolder — so a subfolder/cascade repo is loaded via the package.
-
-## Model details
-
-| | |
-|---|---|
-| Architecture | 3D UNet, velocity-prediction (flow-matching) Euler sampler |
-| Representation | Truncated UDF voxels (direct-diffusion; no VAE). Z is the vertical axis |
-| Conditioning | Waymo vector maps (lanes, road edges/lines, crosswalks); 3D-FRONT layouts (walls/floors/doors/windows/furniture); optional tags (time/weather/location) |
-| Generation | Chunked, coarse→refine cascade; sequential or simultaneous (feather-averaged) |
-| Frameworks | `torch>=2.2`, `diffusers>=0.29` (tested on torch 2.2/diffusers 0.29.2 and torch 2.5/diffusers 0.38) |
-
-## Training data & licensing
-
-The weights are **derived from**:
-- **Waymo Open Dataset** — <https://waymo.com/open/> — non-commercial research license;
-  redistribution of raw data is restricted. The `waymo-*` weights are for research use
-  consistent with the WOD terms.
-- **3D-FRONT** — Alibaba; research license.
-
-Code and weights are Apache-2.0, but **your use must also comply with the upstream
-dataset licenses**. No raw dataset content is redistributed in this repo.
-
-## Citation
-
-If you use WorldFlow3D, please cite the project (see the GitHub repository).
+See the [GitHub repo](https://github.com/princeton-computational-imaging/WorldFlow3D)
+for full docs and the `generate_indoor` CLI.