| --- |
| tags: |
| - 3d |
| - gaussian-splatting |
| - novel-view-synthesis |
| - computer-vision |
| --- |
| |
| <div align="center"> |
|
|
| # InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis |
|
|
| [Project Page](https://pluswave.top/InfiniSplat-page/) | [Code](https://github.com/PLUS-WAVE/InfiniSplat-oss) | [Gallery](https://pluswave.top/InfiniSplat-page/#visualization) |
|
|
| <img src="assets/github_demo.gif" alt="InfiniSplat demo" width="90%" /> |
|
|
| </div> |
|
|
| ## Overview |
|
|
| InfiniSplat reconstructs a 3D Gaussian scene representation from a single image. It supports RGB-only reconstruction and depth-sensor-guided reconstruction from a spatially aligned RGB-depth pair. |
|
|
| | Checkpoint | Input | Output | |
| | --- | --- | --- | |
| | [`infinisplat_rgb.ckpt`](checkpoints/infinisplat_rgb.ckpt) | RGB image | 3D Gaussian Splatting scene | |
| | [`infinisplat_lidar.ckpt`](checkpoints/infinisplat_lidar.ckpt) | RGB image + aligned depth | 3D Gaussian Splatting scene | |
|
|
| The released checkpoints contain the complete inference weights required by their respective encoders. |
|
|
| ## Usage |
|
|
| Clone the [InfiniSplat repository](https://github.com/PLUS-WAVE/InfiniSplat-oss), follow the [installation guide](https://github.com/PLUS-WAVE/InfiniSplat-oss/blob/main/INSTALL.md), and download the checkpoints: |
|
|
| ```bash |
| bash scripts/download_checkpoints.sh |
| ``` |
|
|
| RGB-only inference: |
|
|
| ```bash |
| python -m src.demo.infer_batch_images --input examples/data/rgb_demo/pexels-masi.jpg |
| ``` |
|
|
| Depth-sensor-guided inference: |
|
|
| ```bash |
| python -m src.demo.infer_batch_images \ |
| --mode lidar \ |
| --input examples/data/lidar_demo/eth3d_kicker.png |
| ``` |
|
|
| The input path may also be a directory for batch inference. In LiDAR mode, RGB and depth files are paired by filename stem. See the full [inference guide](https://github.com/PLUS-WAVE/InfiniSplat-oss/blob/main/docs/inference.md) for supported depth formats, camera intrinsics, outputs, and optional arguments. |
|
|
| ## Outputs |
|
|
| Inference always exports a Gaussian PLY. Novel-view MP4 rendering is available when `gsplat` is installed, and interactive HTML export is available when the PlayCanvas `splat-transform` CLI is installed. |
|
|
| ## Acknowledgments |
|
|
| InfiniSplat builds on [DINOv3](https://github.com/facebookresearch/dinov3), [Depth Pro](https://github.com/apple/ml-depth-pro), [InfiniDepth](https://github.com/zju3dv/InfiniDepth), and [gsplat](https://github.com/nerfstudio-project/gsplat). We thank their authors for their excellent work. |
|
|
