Functions — github.com/Inception3D/TTT3R

hub / github.com/Inception3D/TTT3R / functions

Functions1,064 in github.com/Inception3D/TTT3R

⨍ Functions 1,064◇ Types & classes 166

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

viser_utils.py:232

↓ 1 callersFunctioncolorize_np

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

eval/video_depth/utils.py:144

↓ 1 callersFunctioncolorize_np

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

eval/relpose/utils.py:219

↓ 1 callersFunctioncolorize_np

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

src/dust3r/viz.py:505

↓ 1 callersFunctioncompletion

(gt_points, rec_points, gt_normals=None, rec_normals=None)

eval/mv_recon/utils.py:29

↓ 1 callersMethodcompute_frame_loss

(self, gts, preds, **kw)

eval/mv_recon/criterion.py:328

↓ 1 callersMethodcompute_loss

(self, *args, **kwargs)

eval/mv_recon/criterion.py:47

↓ 1 callersMethodcompute_loss

(self, *args, **kwargs)

src/dust3r/losses.py:115

↓ 1 callersFunctioncompute_pointmap

Compute a HxWx3 pointmap in camera frame from a HxW depth map.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:32

↓ 1 callersFunctioncreate_commandline

Create a commandline string to generate a scene.

src/croco/datasets/habitat_sim/generate_multiview_images.py:160

↓ 1 callersFunctioncreate_dpt_head

return PixelwiseTaskWithDPT for given net params

src/dust3r/heads/dpt_head.py:114

↓ 1 callersFunctioncroco_args_from_ckpt

(ckpt)

src/croco/models/croco_downstream.py:13

↓ 1 callersMethodcrop

(self, *args, **kwargs)

eval/mv_recon/dataset_utils/cropping.py:52

↓ 1 callersFunctioncrop_generator

()

src/croco/stereoflow/engine.py:288

↓ 1 callersFunctiondepthmap_to_camera_coordinates

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix Returns: pointmap of absolute coordinates (HxWx3 arra

src/dust3r/utils/geometry.py:177

↓ 1 callersFunctiondisp_to_tensor

(disp)

src/croco/stereoflow/datasets_stereo.py:51

↓ 1 callersMethoddistance

(self, a, b)

eval/mv_recon/criterion.py:113

↓ 1 callersMethoddistance

(self, a, b)

src/dust3r/losses.py:61

↓ 1 callersMethoddistance

(self, pred, gt, mask)

src/dust3r/losses.py:251

↓ 1 callersMethoddistance

(self, pred, gt, mask)

src/dust3r/losses.py:275

↓ 1 callersFunctiondnames_to_image_pairs

dnames: list of datasets with image pairs, separated by +

src/croco/datasets/pairs_dataset.py:90

↓ 1 callersFunctiondrawMatches

(img1, img2, kp1, kp2, radius=2, mask=None, color_by=0, row_cat=False)

src/dust3r/viz.py:662

↓ 1 callersFunctiondrawMatches_lines

( img1, img2, kp1, kp2, radius=2, mask=None, color_by=0, row_cat=False )

src/dust3r/viz.py:738

↓ 1 callersFunctiondrop_path

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

src/dust3r/blocks.py:28

↓ 1 callersFunctiondrop_path

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

src/croco/models/blocks.py:37

↓ 1 callersMethodencode_image_pairs

run encoder for a pair of images it is actually ~5% faster to concatenate the images along the batch dimension than to encode them se

src/croco/models/croco_downstream.py:101

↓ 1 callersFunctioneval_metrics

(pred_traj, gt_traj=None, seq="", filename="", sample_stride=1)

eval/relpose/evo_utils.py:200

↓ 1 callersFunctioneval_pose_estimation

(args, model, save_dir=None)

eval/video_depth/launch.py:75

↓ 1 callersFunctioneval_pose_estimation

(args, model, save_dir=None)

eval/relpose/launch.py:80

↓ 1 callersFunctioneval_pose_estimation_dist

(args, model, img_path, save_dir=None, mask_path=None)

eval/video_depth/launch.py:86

↓ 1 callersFunctioneval_pose_estimation_dist

(args, model, img_path, save_dir=None, mask_path=None)

eval/relpose/launch.py:91

↓ 1 callersFunctionextract_correspondences_from_pts3d

( view1, view2, target_n_corres, rng=np.random, ret_xy=True, nneg=0 )

src/dust3r/datasets/utils/corr.py:55

↓ 1 callersFunctionextract_metrics

(file_path)

eval/relpose/evo_utils.py:412

↓ 1 callersFunctionfill_default_args

(kwargs, func)

src/dust3r/utils/misc.py:10

↓ 1 callersMethodfinalize_submission

(self, outdir)

src/croco/stereoflow/datasets_flow.py:522

↓ 1 callersFunctionflowMaxNorm

flow_utils.flowMaxNorm(flow): return the maximum of the l2-norm of the given flow ---- PARAMETERS ---- flow: the flow ---- OUTPU

src/croco/stereoflow/datasets_flow.py:839

↓ 1 callersFunctionflowToColor

flow_utils.flowToColor(flow): return a color code flow field, normalized based on the maximum l2-norm of the flow flow_utils.flowToColor(flow

src/croco/stereoflow/datasets_flow.py:808

↓ 1 callersFunctionflow_to_tensor

(disp)

src/croco/stereoflow/datasets_flow.py:36

↓ 1 callersMethodforward_recurrent

(self, views, device, ret_state=False)

src/dust3r/model.py:1003

↓ 1 callersMethodforward_recurrent_lighter

(self, views, device='cuda', ret_state=False)

src/dust3r/model.py:1143

↓ 1 callersFunctionfreeze_all_params

(modules)

src/dust3r/utils/misc.py:23

↓ 1 callersFunctiongen_mask_indicator

(img_mask_list, ray_mask_list, num_views, h, w)

src/train.py:653

↓ 1 callersFunctiongenerate_multiview_images_for_scene

Generate tuples of overlapping views for a given scene. generate_depth: generate depth images and camera parameters.

src/croco/datasets/habitat_sim/generate_multiview_images.py:20

↓ 1 callersFunctiongenerate_multiview_images_from_metadata

Generate images from a metadata file for reproducibility purposes.

src/croco/datasets/habitat_sim/generate_from_metadata.py:20

↓ 1 callersMethodgenerate_pseudo_intrinsics

(h, w)

viser_utils.py:600

↓ 1 callersMethodgenerate_sequence

( self, scene, adj_list, num_views, start_index, rng, allow_repeat=False )

src/dust3r/datasets/blendedmvs.py:194

↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid

(embed_dim, grid)

src/croco/models/pos_embed.py:42

↓ 1 callersFunctionget_args_parser

()

eval/video_depth/eval_depth.py:16

↓ 1 callersFunctionget_args_parser

()

eval/video_depth/launch.py:20

↓ 1 callersFunctionget_args_parser

()

eval/relpose/launch.py:21

↓ 1 callersFunctionget_args_parser

()

eval/mv_recon/launch.py:19

↓ 1 callersFunctionget_args_parser

()

src/croco/pretrain.py:37

↓ 1 callersFunctionget_args_parser

()

src/croco/stereoflow/train.py:40

↓ 1 callersFunctionget_args_parser

()

src/croco/stereoflow/test.py:31

↓ 1 callersMethodget_conf_log

(self, x)

eval/mv_recon/criterion.py:419

↓ 1 callersMethodget_cos_sin

(self, D, seq_len, device, dtype)

src/croco/models/pos_embed.py:134

↓ 1 callersFunctionget_data_loader

( dataset, batch_size, num_workers=8, shuffle=True, drop_last=True, pin_mem=True,

src/dust3r/datasets/__init__.py:41

↓ 1 callersFunctionget_grad_norm_

(parameters, norm_type: float = 2.0)

src/croco/utils/misc.py:369

↓ 1 callersFunctionget_med_dist_between_poses

(poses)

src/dust3r/utils/geometry.py:510

↓ 1 callersMethodget_output_dim

Same as above. The default for input_dims is 3 for 3D applications which use harmonic embedding for positional encoding, so t

src/dust3r/utils/camera.py:243

↓ 1 callersMethodget_output_dim_static

Utility to help predict the shape of the output of `forward`. Args: input_dims: length of the last dimension of the inpu

src/dust3r/utils/camera.py:227

↓ 1 callersFunctionget_pair_transforms

(transform_str, totensor=True, normalize=True)

src/croco/datasets/transforms.py:101

↓ 1 callersFunctionget_path

(idx)

src/croco/datasets/crops/extract_crops_from_images.py:98

↓ 1 callersFunctionget_pred_pts3d

(gt, pred, use_pose=False)

eval/mv_recon/criterion.py:127

↓ 1 callersFunctionget_ray_map

(c2w1, c2w2, intrinsics, h, w)

src/dust3r/datasets/base/base_multiview_dataset.py:13

↓ 1 callersMethodget_results

(self)

src/croco/stereoflow/criterion.py:349

↓ 1 callersMethodget_stats

(self)

eval/mv_recon/base.py:51

↓ 1 callersMethodget_stats

(self)

src/dust3r/datasets/base/base_multiview_dataset.py:309

↓ 1 callersFunctionget_vertical_colorbar

:param w: pixels :param h: pixels :param vmin: min value :param vmax: max value :param cmap_name: :param label :return:

viser_utils.py:185

↓ 1 callersFunctionget_vertical_colorbar

:param w: pixels :param h: pixels :param vmin: min value :param vmax: max value :param cmap_name: :param label :return:

eval/video_depth/utils.py:94

↓ 1 callersFunctionget_vertical_colorbar

:param w: pixels :param h: pixels :param vmin: min value :param vmax: max value :param cmap_name: :param label :return:

eval/relpose/utils.py:169

↓ 1 callersFunctionget_vertical_colorbar

:param w: pixels :param h: pixels :param vmin: min value :param vmax: max value :param cmap_name: :param label :return:

src/dust3r/viz.py:456

↓ 1 callersFunctionget_world_size

()

src/croco/utils/misc.py:226

↓ 1 callersFunctionhead_factory

" build a prediction head for the decoder

src/dust3r/heads/__init__.py:11

↓ 1 callersMethodimg_loss

(self, a, b)

src/dust3r/losses.py:202

↓ 1 callersMethodimgid2path

(self, img_id, scene)

src/dust3r/datasets/mapfree.py:29

↓ 1 callersMethodinference_step

( self, view, state_feat, state_pos, init_state_feat, mem, init_mem )

src/dust3r/model.py:940

↓ 1 callersMethodinitialize_weights

(self)

src/croco/models/croco.py:191

↓ 1 callersFunctioninterpolate_pos_embed

(model, checkpoint_model)

src/croco/models/pos_embed.py:80

↓ 1 callersFunctionis_good_type

returns (is_good, err_msg)

eval/mv_recon/base.py:236

↓ 1 callersFunctionis_good_type

returns (is_good, err_msg)

src/dust3r/datasets/base/base_multiview_dataset.py:498

↓ 1 callersFunctionis_main_process

(accelerator: Accelerator)

src/croco/utils/misc.py:238

↓ 1 callersMethodis_other_viewpoint_overlapping

Check if a viewpoint is valid and overlaps significantly with a reference one.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:322

↓ 1 callersMethodis_reachable

(adjacency_list, start_index, k)

src/dust3r/datasets/blendedmvs.py:66

↓ 1 callersFunctionlist_replica_cad_baked_lighting_scenes

( base_output_dir, base_path=SCENES_DATASET["replica_cad_baked_lighting"] )

src/croco/datasets/habitat_sim/paths.py:52

↓ 1 callersFunctionlist_replica_scenes

(base_output_dir, base_path)

src/croco/datasets/habitat_sim/paths.py:77

↓ 1 callersFunctionlist_scenes_available

(base_output_dir, scenes_dataset_paths=SCENES_DATASET)

src/croco/datasets/habitat_sim/paths.py:141

↓ 1 callersMethodload_all_scenes

(self, base_dir)

eval/mv_recon/data.py:75

↓ 1 callersMethodload_all_scenes

(self, base_dir)

eval/mv_recon/data.py:230

↓ 1 callersMethodload_all_scenes

(self, base_dir)

eval/mv_recon/data.py:422

↓ 1 callersMethodload_all_tuples

(self, tuple_list)

eval/mv_recon/data.py:66

↓ 1 callersMethodload_all_tuples

(self, tuple_list)

eval/mv_recon/data.py:413

↓ 1 callersMethodload_cam_mvsnet

read camera txt file

eval/mv_recon/data.py:244

↓ 1 callersFunctionload_crop_file

(path)

src/croco/datasets/crops/extract_crops_from_images.py:75

↓ 1 callersFunctionload_image

(path)

src/croco/datasets/crops/extract_crops_from_images.py:118

↓ 1 callersMethodload_invalid_dict

(self, h5_file_path)

src/dust3r/datasets/waymo.py:24

↓ 1 callersFunctionload_iphone_traj

(gt_file)

eval/relpose/evo_utils.py:102

↓ 1 callersFunctionload_model

(model_path, device, verbose=True)

src/dust3r/model.py:74

↓ 1 callersFunctionload_pairs_from_cache_file

(fname, root="")

src/croco/datasets/pairs_dataset.py:15

↓ 1 callersFunctionload_pairs_from_list_file

(fname, root="")

src/croco/datasets/pairs_dataset.py:28

← previous next →301–400 of 1,064, ranked by callers