Changes for CO3Dv2 release [part1]

Summary:
Implements several changes needed for the CO3Dv2 release:
- FrameData contains crop_bbox_xywh which defines the outline of the image crop corresponding to the image-shaped tensors in FrameData
- revised the definition of a bounding box inside JsonDatasetIndex: bbox_xyxy is [xmin, ymin, xmax, ymax], where xmax, ymax are not inclusive; bbox_xywh = [xmin, ymain, xmax-xmin, ymax-ymin]
- is_filtered for detecting whether the entries of the dataset were somehow filtered
- seq_frame_index_to_dataset_index allows to skip entries that are not present in the dataset

Reviewed By: shapovalov

Differential Revision: D37687547

fbshipit-source-id: 7842756b0517878cc0964fc0935d3c0769454d78

tests/implicitron/test_dataset_visualize.py

@@ -14,6 +14,7 @@ import torch
 import torchvision
 from pytorch3d.implicitron.dataset.json_index_dataset import JsonIndexDataset
 from pytorch3d.implicitron.dataset.visualize import get_implicitron_sequence_pointcloud
+from pytorch3d.implicitron.tools.config import expand_args_fields
 from pytorch3d.implicitron.tools.point_cloud_utils import render_point_cloud_pytorch3d
 from pytorch3d.vis.plotly_vis import plot_scene
 
@@ -37,6 +38,7 @@ class TestDatasetVisualize(unittest.TestCase):
         frame_file = os.path.join(dataset_root, category, "frame_annotations.jgz")
         sequence_file = os.path.join(dataset_root, category, "sequence_annotations.jgz")
         self.image_size = 256
+        expand_args_fields(JsonIndexDataset)
         self.datasets = {
             "simple": JsonIndexDataset(
                 frame_annotations_file=frame_file,