Attention des changements sont bientôt à prévoir sur l'instance gitea d'Aurore :
@ -2,7 +2,7 @@
Codebase for paper:
* Work with 360 capture of large-scale unbounded scenes.
* Support multi-gpu training and inference with PyTorch DistributedDataParallel (DDP).
* Optimize per-image autoexposure (ongoing work)
* Optimize per-image autoexposure (*experimental feature*)
## Data
* Download our preprocessed data from [tanks_and_temples](https://drive.google.com/file/d/11KRfN91W1AxAW6lOFs4EeYDbeoQZCi87/view?usp=sharing), [lf_data](https://drive.google.com/file/d/1gsjDjkbTh4GAR9fFqlIDZ__qR9NYTURQ/view?usp=sharing).
@ -28,4 +28,4 @@ python ddp_train_nerf.py --config configs/tanks_and_temples/tat_training_truck.t
```python
python ddp_test_nerf.py --config configs/tanks_and_temples/tat_training_truck.txt \
--render_splits test,camera_path
```