Refresh model card from release source

README.md

@@ -17,45 +17,58 @@ tags:
   - arxiv:2609.06948
 ---
 
-<div align="center">
-
 # PRG-Fusion
 
-## Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis
+**Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis**
 
-**Sipeng He · Jialei Chen · Zhen Fang · Dongchun Ren · Feng Zhao**
+Sipeng He<sup>1</sup> · Jialei Chen<sup>2</sup> · Zhen Fang<sup>1</sup> · Dongchun Ren<sup>2</sup> · Feng Zhao<sup>1</sup>
 
-[Paper](https://arxiv.org/abs/2609.06948) · [Code](https://github.com/Pre-cici/PRG-Fusion)
+<sup>1</sup>University of Science and Technology of China · <sup>2</sup>Yootta
 
-</div>
+[Project page](https://pre-cici.github.io/PRG-Fusion/) · [Paper](https://arxiv.org/abs/2609.06948) · [Code](https://github.com/Pre-cici/PRG-Fusion)
 
-PRG-Fusion synthesizes photorealistic driving videos along novel trajectories by combining reconstruction evidence with generative video priors. It uses dense 3D Gaussian Splatting (3DGS) renderings for appearance control and sparse LiDAR projections for geometric control.
+PRG-Fusion synthesizes driving videos along novel trajectories using dense 3D Gaussian Splatting (3DGS) renderings and sparse colored LiDAR projections. This repository provides the **PRG-Fusion model checkpoint**; inference also requires the code, component checkpoints, and aligned control inputs described below.
 
 ![PRG-Fusion pipeline](assets/pipeline.png)
 
-PRG-Fusion converts region-wise reconstruction degradation evidence into **Preserve, Repair, and Generate (PRG)** labels. These labels route information across the video diffusion model:
+Region-wise reconstruction evidence produces **Preserve, Repair, and Generate (PRG)** labels that route appearance, geometry, and generative priors:
 
 - **Preserve** reliable appearance from dense 3DGS renderings.
 - **Repair** uncertain geometry using sparse LiDAR projections.
 - **Generate** missing content with video priors.
 
-The model follows a two-stage training strategy: geometric control is first learned from sparse LiDAR projections, followed by appearance control from dense 3DGS renderings.
+Training proceeds in two stages: geometric control is learned from sparse LiDAR projections, followed by appearance control from dense 3DGS renderings.
 
 ## Model Details
 
 | | |
 | --- | --- |
-| **Model** | PRG-Fusion |
+| **Model** | PRG-Fusion (2B base with two control branches) |
 | **Base model** | [NVIDIA Cosmos-Transfer2.5-2B](https://huggingface.co/nvidia/Cosmos-Transfer2.5-2B) |
-| **Conditioning** | Dense 3DGS renderings and sparse LiDAR projections |
+| **Conditioning** | Aligned 3DGS rendering, colored LiDAR projection, PRG region labels, and a text prompt |
 | **Checkpoint format** | PyTorch Distributed Checkpoint (DCP) |
-| **Input** | Text prompt and aligned target-trajectory control videos |
-| **Output** | Novel-trajectory driving video |
+| **Demo output** | One 93-frame, 960 × 640 driving video chunk |
+| **Inference hardware** | Approximately 70 GB GPU memory; use an 80 GB-class NVIDIA GPU |
 | **Evaluation domain** | Waymo driving scenes |
 
-## Download
+## Set Up the Code
 
-Download the checkpoint directly into the layout expected by the PRG-Fusion code:
+Use a Linux x86-64 host with an 80 GB-class NVIDIA GPU, a compatible CUDA driver, FFmpeg, and [uv](https://docs.astral.sh/uv/). Clone the [PRG-Fusion code](https://github.com/Pre-cici/PRG-Fusion) and install the CUDA 13.0 environment:
+
+```bash
+git clone https://github.com/Pre-cici/PRG-Fusion.git
+cd PRG-Fusion
+
+uv venv --python 3.10
+uv sync --extra cu130
+uv run --extra cu130 python examples/check_environment.py
+```
+
+Use `cu128` instead of `cu130` on a CUDA 12.8 system.
+
+## Download the Checkpoint
+
+From the code repository root, download the model checkpoint into the expected layout:
 
 ```bash
 uv tool install -U huggingface_hub
@@ -75,40 +88,29 @@ checkpoints/PRG-Fusion/
 │   └── __1_0.distcp
 ```
 
-All three files are required. Keep the original filenames because `.metadata` references the two DCP shards.
-
-## Usage
-
-Clone and install the [PRG-Fusion code](https://github.com/Pre-cici/PRG-Fusion) on a Linux NVIDIA GPU host:
+All three files are required. Keep the original filenames: `.metadata` references the two DCP shards. The pinned revision matches the [code repository's checkpoint guide](https://github.com/Pre-cici/PRG-Fusion/blob/main/docs/checkpoints.md).
 
-```bash
-git clone https://github.com/Pre-cici/PRG-Fusion.git
-cd PRG-Fusion
-
-uv venv --python 3.10
-uv sync --extra cu130
-uv run --extra cu130 python examples/check_environment.py
-```
+## Run the Demo
 
-Use `cu128` instead of `cu130` on a CUDA 12.8 system. Follow the repository's [checkpoint guide](https://github.com/Pre-cici/PRG-Fusion/blob/main/docs/checkpoints.md) to download the remaining Cosmos tokenizer and text-conditioning components.
+In addition to the PRG-Fusion checkpoint above, download the Cosmos tokenizer, text encoder, and initialization weights using the [checkpoint guide](https://github.com/Pre-cici/PRG-Fusion/blob/main/docs/checkpoints.md). Weights are not bundled with the code repository.
 
 The demo inputs ship with the repository in `assets/demo/`:
 
 ```text
 assets/demo/
-├── vis.mp4                  # Dense 3DGS renderings for appearance control
-├── lidar.mp4                # Sparse colored LiDAR projections for geometric control
-└── prg/                     # Lossless PRG region labels (preserve / repair / generate) for the dense gate
+├── vis.mp4                  # Dense 3DGS rendering for appearance control
+├── lidar.mp4                # Sparse colored LiDAR projection for geometric control
+└── prg/                     # PRG region labels used by the dense gate
 ```
 
-The demo configuration runs one 93-frame chunk at 960 × 640. To synthesize other trajectories, prepare an aligned 3DGS rendering, a sparse colored LiDAR projection, and PRG region labels in the same layout. Then run:
+The two control videos and PRG labels must be aligned frame by frame on the target trajectory. The demo uses 93 frames at 960 × 640; labels encode preserve (0), repair (1), and generate (2). For other trajectories, prepare inputs in the same layout, then run from the code repository root:
 
 ```bash
 uv run --extra cu130 python examples/inference.py \
   --config configs/inference/demo.yaml
 ```
 
-Generated videos and run metadata are written to `outputs/debug/<timestamp>_demo/` by default.
+Generated videos and run metadata are written to `outputs/debug/<timestamp>_demo/` by default. See the [inference guide](https://github.com/Pre-cici/PRG-Fusion/blob/main/docs/inference.md) for input and path semantics.
 
 ## Checkpoint Integrity
 
@@ -120,7 +122,7 @@ Generated videos and run metadata are written to `outputs/debug/<timestamp>_demo
 
 ## Limitations
 
-The model is designed for research on driving view synthesis. Generated videos may contain temporal, geometric, or appearance artifacts, especially under large viewpoint changes or in regions with limited reconstruction evidence. It is not intended for safety-critical driving decisions.
+The model is intended for research on driving view synthesis, not safety-critical driving decisions. It was evaluated on Waymo driving scenes; performance on other domains has not been established here. Large viewpoint changes or weak reconstruction evidence may cause temporal, geometric, or appearance artifacts. The checkpoint does not generate the required 3DGS, LiDAR, or PRG-label inputs for you.
 
 ## Acknowledgements
 
@@ -128,7 +130,7 @@ We thank the NVIDIA Cosmos team for making their work available. We also thank t
 
 ## License
 
-PRG-Fusion is a derivative of NVIDIA Cosmos-Transfer2.5-2B and is released under the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). **Built on NVIDIA Cosmos.** See [LICENSE.pdf](LICENSE.pdf) and [NOTICE](NOTICE) for details.
+The **model weights** are a derivative of NVIDIA Cosmos-Transfer2.5-2B and are distributed under the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). **Built on NVIDIA Cosmos.** See [LICENSE.pdf](LICENSE.pdf) and [NOTICE](NOTICE) for details. The separate code repository uses Apache-2.0; dataset and media rights are separate from the model license.
 
 ## Citation