The command provided, bash scripts/infer_spatialgen_i2s.sh, is intended to convert a single image into a 3D scene. However, the configuration file specifies that the input should be a scene containing multiple RGB images, as well as various formats such as depth maps, layout semantic maps, semantic maps, and room layout JSON files.
The configuration file is structured as follows:
dataset_names: [“spatialgen”]
test_data_dir: “/seaweedfs/training/experiments/zhenqing/spatialgen-publish/SpatialGen/example_data/scenes”
test_split_file: “/seaweedfs/training/experiments/zhenqing/spatialgen-publish/SpatialGen/example_data/scenes/test_split.txt”
Could you please clarify if the provided command is suitable for inputting only a single image?
The command provided,
bash scripts/infer_spatialgen_i2s.sh, is intended to convert a single image into a 3D scene. However, the configuration file specifies that the input should be a scene containing multiple RGB images, as well as various formats such as depth maps, layout semantic maps, semantic maps, and room layout JSON files.The configuration file is structured as follows:
Could you please clarify if the provided command is suitable for inputting only a single image?