Functions — github.com/Inception3D/TTT3R

hub / github.com/Inception3D/TTT3R / functions

Functions1,064 in github.com/Inception3D/TTT3R

⨍ Functions 1,064◇ Types & classes 166

↓ 3 callersMethodload_state_dict

(self, ckpt, **kw)

src/dust3r/model.py:395

↓ 3 callersFunctionloss_of_one_batch

( batch, model, criterion, accelerator: Accelerator, symmetrize_batch=False, use_amp=F

src/dust3r/inference.py:55

↓ 3 callersMethodparse_pc_data

( self, pc, color, conf=None, edge_color=[0.251, 0.702, 0.902],

viser_utils.py:780

↓ 3 callersFunctionreg_dense_depth

extract 3D points from prediction head output

src/dust3r/heads/postprocess.py:113

↓ 3 callersFunctionsel

(x)

eval/mv_recon/base.py:246

↓ 3 callersFunctionsel

(x)

src/dust3r/datasets/base/base_multiview_dataset.py:508

↓ 3 callersFunctionstrip_module

Removes the 'module.' prefix from the keys of a state_dict. Args: state_dict (dict): The original state_dict with possible 'module.'

src/dust3r/model.py:59

↓ 3 callersMethodto_pil

(self)

eval/mv_recon/dataset_utils/cropping.py:40

↓ 3 callersMethodto_pil

(self)

src/dust3r/datasets/utils/cropping.py:41

↓ 3 callersFunctiontodevice

Transfer some variables to another device (i.e. GPU, CPU:torch, CPU:numpy). batch: list, tuple, dict of tensors or other things device: pytor

src/dust3r/utils/device.py:11

↓ 2 callersFunctionSeqColorJitter

Return a color jitter transform with same random parameters

src/dust3r/datasets/utils/transforms.py:41

↓ 2 callersFunctionSum

(*losses_and_masks)

src/dust3r/losses.py:27

↓ 2 callersMethod__call__

(self, img1, img2)

src/croco/datasets/transforms.py:13

↓ 2 callersMethod__init__

( self, num_seq=49, num_frames=5, min_thresh=10, max_thresh=30,

eval/mv_recon/data.py:198

↓ 2 callersMethod__init__

( self, size, k_dim, v_dim, num_heads, depth=2, mlp_ra

src/dust3r/model.py:145

↓ 2 callersFunction_computeColor

flow_utils._computeColor(flow): compute color codes for the flow field flow ---- PARAMETERS ---- flow: np.array of dimension (height

src/croco/stereoflow/datasets_flow.py:851

↓ 2 callersMethod_decoder

return_all_blocks: if True, return the features at the end of every block instead of just the features from the la

src/croco/models/croco.py:247

↓ 2 callersMethod_dispatch

(self, func, *args, **kwargs)

eval/mv_recon/dataset_utils/cropping.py:55

↓ 2 callersMethod_dispatch

(self, func, *args, **kwargs)

src/dust3r/datasets/utils/cropping.py:56

↓ 2 callersMethod_encode_image

image has B x 3 x img_size x img_size do_mask: whether to perform masking or not return_all_blocks: if True, return the featu

src/croco/models/croco.py:210

↓ 2 callersMethod_encode_views

(self, views, img_mask=None, ray_mask=None)

src/dust3r/model.py:579

↓ 2 callersMethod_error

(self, gt, predictions)

src/croco/stereoflow/criterion.py:30

↓ 2 callersMethod_forward_decoder_step

( self, views, i, feat_i, pos_i, shape_i, init_state_f

src/dust3r/model.py:767

↓ 2 callersMethod_forward_impl

(self, views, ret_state=False)

src/dust3r/model.py:835

↓ 2 callersFunction_interleave_imgs

(img1, img2)

src/dust3r/inference.py:37

↓ 2 callersFunction_overlapping

(total, window, overlap=0.5)

src/croco/stereoflow/engine.py:353

↓ 2 callersFunction_read_pfm

(file)

src/croco/stereoflow/datasets_stereo.py:886

↓ 2 callersMethod_resize_flow

(self, flow, scale_x, scale_y, factor=1.0)

src/croco/stereoflow/augmentor.py:290

↓ 2 callersFunction_resize_img

(img, new_size)

src/croco/stereoflow/engine.py:225

↓ 2 callersFunction_resize_stereo_or_flow

(data, new_size)

src/croco/stereoflow/engine.py:229

↓ 2 callersMethodadapt_tokens

(self, encoder_tokens)

src/croco/models/dpt_block.py:471

↓ 2 callersMethodadd_pointcloud

(self, pts3d, color=(0, 0, 0), mask=None, denoise=False)

src/dust3r/viz.py:165

↓ 2 callersMethodapply_rope1d

(self, tokens, pos1d, cos, sin)

src/croco/models/pos_embed.py:152

↓ 2 callersFunctionarea

(sz)

src/croco/datasets/crops/extract_crops_from_images.py:136

↓ 2 callersMethodblockwise_shuffle

(x, rng, block_shuffle)

src/dust3r/datasets/base/base_multiview_dataset.py:168

↓ 2 callersFunctionbuild_dataset

(dataset, batch_size, num_workers, accelerator, test=False, fixed_length=False)

src/train.py:355

↓ 2 callersFunctioncat

(a, b)

src/dust3r/viz.py:390

↓ 2 callersFunctioncat_3d

(vecs)

src/dust3r/viz.py:39

↓ 2 callersFunctioncolmap_to_opencv_intrinsics

Modify camera intrinsics to follow a different convention. Coordinates of the center of the top-left pixels are by default: - (0.5, 0.5)

src/dust3r/utils/geometry.py:235

↓ 2 callersFunctioncolorize

turn a grayscale image into a color image :param x: torch.Tensor, grayscale image, [H, W] or [B, H, W] :param mask: torch.Tensor or None,

eval/video_depth/utils.py:208

↓ 2 callersFunctioncolorize

turn a grayscale image into a color image :param x: torch.Tensor, grayscale image, [H, W] or [B, H, W] :param mask: torch.Tensor or None,

eval/relpose/utils.py:283

↓ 2 callersFunctioncompute_camera_intrinsics

(height, width, hfov)

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

↓ 2 callersFunctioncompute_pointcloud_overlaps_scikit

Compute 'overlapping' metrics based on a distance threshold between two point clouds.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:59

↓ 2 callersMethodcompute_pose_loss

gt_pose: list of (Bx3, Bx4) pred_pose: list of (Bx3, Bx4) masks: None, or B

src/dust3r/losses.py:737

↓ 2 callersMethodforward

(self, img1, img2)

src/croco/datasets/transforms.py:20

↓ 2 callersFunctiongenerate_orientation_noise

(pan_range, tilt_range, roll_range)

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:125

↓ 2 callersFunctionget_1d_sincos_pos_embed_from_grid

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

src/croco/models/pos_embed.py:53

↓ 2 callersFunctionget_2d_sincos_pos_embed

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [n_cls_token+grid_size*grid_size, embe

src/croco/models/pos_embed.py:22

↓ 2 callersMethodget_conf_log

(self, x)

src/dust3r/losses.py:1067

↓ 2 callersFunctionget_joint_pointcloud_center_scale

(pts, valid_masks=None, z_only=False, center=True)

eval/mv_recon/criterion.py:254

↓ 2 callersFunctionget_joint_pointcloud_depth

(zs, valid_masks=None, quantile=0.5)

eval/mv_recon/criterion.py:235

↓ 2 callersMethodget_name

(self)

eval/mv_recon/criterion.py:50

↓ 2 callersMethodget_name

(self)

src/dust3r/losses.py:118

↓ 2 callersMethodget_name

(self)

src/dust3r/losses.py:1064

↓ 2 callersFunctionget_norm_factor

(pts, norm_mode="avg_dis", valids=None, fix_first=True)

eval/mv_recon/criterion.py:168

↓ 2 callersFunctionget_patch_embed

(patch_embed_cls, img_size, patch_size, enc_embed_dim, in_chans=3)

src/dust3r/patch_embed.py:12

↓ 2 callersFunctionget_tum_poses

poses: list of 4x4 arrays

eval/relpose/utils.py:74

↓ 2 callersFunctionget_vis_imgs_new

(loss_details, num_imgs_vis, num_views, is_metric)

src/train.py:768

↓ 2 callersFunctionimg_to_arr

(img)

src/dust3r/utils/image.py:28

↓ 2 callersMethodinit

Initialize parts of decoder that are dependent on dimension of encoder tokens. Should be called when setting up MultiMAE. :p

src/croco/models/dpt_block.py:380

↓ 2 callersFunctionis_dist_avail_and_initialized

()

src/croco/utils/misc.py:218

↓ 2 callersMethodis_other_pointcloud_overlapping

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

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:301

↓ 2 callersMethodjitter_one

( self, img, fn_idx, brightness_factor, contrast_factor, satur

src/croco/datasets/transforms.py:47

↓ 2 callersFunctionlistify

(elems)

src/dust3r/utils/device.py:87

↓ 2 callersFunctionload_image

(impath)

src/croco/datasets/pairs_dataset.py:11

↓ 2 callersFunctionload_timestamps

(time_file, traj_format="replica")

eval/relpose/evo_utils.py:178

↓ 2 callersFunctionload_traj

Read trajectory format. Return in TUM-RGBD format. Returns: traj_tum (N, 7): camera to world poses in (x,y,z,qx,qy,qz,qw) timestam

eval/relpose/evo_utils.py:137

↓ 2 callersFunctionlook_at_for_habitat

(eye, center, up, return_cam2world=True)

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:119

↓ 2 callersFunctionmake_batch_symmetric

(batch)

src/dust3r/inference.py:49

↓ 2 callersFunctionmerge_chunk_dict

(old_dict, curr_dict, add_number)

src/dust3r/inference.py:20

↓ 2 callersFunctionnorm

(p)

eval/mv_recon/dataset_utils/corr.py:96

↓ 2 callersFunctionnorm

(p)

src/dust3r/datasets/utils/corr.py:102

↓ 2 callersFunctionnormalize_pointcloud_t

( pts, norm_mode="avg_dis", valids=None, fix_first=True, gt=False )

eval/mv_recon/criterion.py:208

↓ 2 callersFunctionopencv_to_colmap_intrinsics

Modify camera intrinsics to follow a different convention. Coordinates of the center of the top-left pixels are by default: - (0.5, 0.5)

src/dust3r/utils/geometry.py:248

↓ 2 callersFunctionplot_trajectory

( pred_traj, gt_traj=None, title="", filename="", align=True, correct_scale=True )

eval/relpose/evo_utils.py:370

↓ 2 callersFunctionprepare_crop

(img, rect, rot=0)

src/croco/datasets/crops/extract_crops_from_images.py:141

↓ 2 callersFunctionprocess_bonn

(args, img_path)

eval/video_depth/metadata.py:159

↓ 2 callersFunctionprocess_kitti

(args, img_path)

eval/video_depth/metadata.py:152

↓ 2 callersFunctionread_file_list

Reads a trajectory from a text file. File format: The file format is "stamp d1 d2 d3 ...", where stamp denotes the time stamp (to b

datasets_preprocess/long_prepare_tum.py:6

↓ 2 callersFunctionrelative_pose_absT_quatR

Compute the relative translation and quaternion between two poses.

src/dust3r/utils/camera.py:453

↓ 2 callersFunctionrender

( intrinsics: torch.Tensor, pts3d: torch.Tensor, rgbs: torch.Tensor | None = None, scale: floa

src/dust3r/utils/render.py:6

↓ 2 callersMethodreorg

(self, ls_b, masks_b)

src/dust3r/losses.py:888

↓ 2 callersFunctionreproject_view

(pts3d, view2)

eval/mv_recon/dataset_utils/corr.py:11

↓ 2 callersFunctionreproject_view

(pts3d, view2)

src/dust3r/datasets/utils/corr.py:12

↓ 2 callersFunctionrgb

(ftensor, true_shape=None)

src/dust3r/utils/image.py:46

↓ 2 callersMethodsample_random_viewpoint

Sample a random viewpoint using the navmesh

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:259

↓ 2 callersMethodselect_scene

(self, scene, *instances, opposite=False)

src/dust3r/datasets/megadepth.py:44

↓ 2 callersFunctionselout

(ar)

src/dust3r/utils/misc.py:82

↓ 2 callersMethodsetup

(self, croconet)

src/croco/models/head_downstream.py:44

↓ 2 callersFunctionsetup_for_distributed

This function disables printing when not in master process

src/croco/utils/misc.py:201

↓ 2 callersMethodshow

(self, point_size=2)

src/dust3r/viz.py:266

↓ 2 callersFunctionshuffle_deque

(dq, seed=None)

eval/mv_recon/data.py:13

↓ 2 callersFunctionsplit_prediction_conf

(predictions, with_conf=False)

src/croco/stereoflow/engine.py:18

↓ 2 callersMethodsynchronize_between_processes

(self, accelerator)

src/croco/utils/misc.py:124

↓ 2 callersFunctiontiled_pred

( model, criterion, img1, img2, gt, overlap=0.5, bad_crop_thr=0.05, downscale=

src/croco/stereoflow/engine.py:243

↓ 2 callersFunctiontransposed

(dic)

src/dust3r/utils/misc.py:105

↓ 2 callersFunctionuint8

(colors)

src/dust3r/viz.py:412

↓ 2 callersMethodupdate

(self, value, n=1)

src/croco/utils/misc.py:43

↓ 2 callersFunctionwriteFlowKitti

(filename, uv)

src/croco/stereoflow/datasets_flow.py:756

↓ 2 callersFunctionwritePFM

(file, image, scale=1)

src/croco/stereoflow/datasets_stereo.py:924

← previous next →101–200 of 1,064, ranked by callers