Functions — github.com/Inception3D/TTT3R

hub / github.com/Inception3D/TTT3R / functions

Functions1,064 in github.com/Inception3D/TTT3R

⨍ Functions 1,064◇ Types & classes 166

↓ 1 callersMethodload_poses

(self, path)

eval/mv_recon/data.py:436

↓ 1 callersFunctionload_replica_traj

(gt_file)

eval/relpose/evo_utils.py:42

↓ 1 callersFunctionload_sintel_traj

(gt_file)

eval/relpose/evo_utils.py:71

↓ 1 callersFunctionlook_at

Return camera pose looking at a given center point. Analogous of gluLookAt function, using OpenCV camera convention.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:96

↓ 1 callersFunctionloss_of_one_batch_tbptt

( batch, model, criterion, chunk_size, loss_scaler, optimizer, accelerator: Accele

src/dust3r/inference.py:90

↓ 1 callersFunctionmain

()

demo.py:512

↓ 1 callersFunctionmain

(args)

eval/video_depth/eval_depth.py:37

↓ 1 callersFunctionmain

(args)

eval/mv_recon/launch.py:47

↓ 1 callersFunctionmain

(args)

src/croco/pretrain.py:156

↓ 1 callersFunctionmain

(args)

src/croco/stereoflow/train.py:198

↓ 1 callersFunctionmain

(args)

src/croco/stereoflow/test.py:165

↓ 1 callersFunctionmain

(args)

src/croco/datasets/crops/extract_crops_from_images.py:46

↓ 1 callersMethodmake_sampler

( self, batch_size, shuffle=True, drop_last=True, world_size=1, rank=0, fixed_length=False )

src/dust3r/datasets/base/easy_dataset.py:38

↓ 1 callersFunctionmake_scratch

(in_shape, out_shape, groups=1, expand=False)

src/croco/models/dpt_block.py:22

↓ 1 callersFunctionmatrix_cumprod

(matrices)

src/dust3r/utils/geometry.py:558

↓ 1 callersFunctionmatrix_to_quaternion

Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re

src/dust3r/utils/camera.py:280

↓ 1 callersMethodmodulate

(x, shift, scale)

src/dust3r/blocks.py:408

↓ 1 callersFunctionpair

(t)

src/croco/models/dpt_block.py:18

↓ 1 callersFunctionparallel_threads

tqdm but with parallel execution. Will essentially return res = [ function(arg) # default function(*arg) # if star_args is Tr

src/dust3r/utils/parallel.py:12

↓ 1 callersFunctionparse_and_cache_all_pairs

(dname, data_dir="./data/")

src/croco/datasets/pairs_dataset.py:57

↓ 1 callersFunctionparse_args

Parse command-line arguments.

demo.py:45

↓ 1 callersMethodparse_pc_data

(self, pc, batch_idx=-1)

src/dust3r/viz.py:897

↓ 1 callersFunctionparse_seq_path

(p, frame_interval=1)

demo.py:369

↓ 1 callersMethodpath2imgid

(self, subscene, filename)

src/dust3r/datasets/mapfree.py:39

↓ 1 callersFunctionpostprocess_desc

extract 3D points/confidence from prediction head output

src/dust3r/heads/postprocess.py:71

↓ 1 callersFunctionpostprocess_pose_conf

(out)

src/dust3r/heads/postprocess.py:66

↓ 1 callersFunctionprepare_input

Prepare input views for inference from a list of image paths. Args: img_paths (list): List of image file paths. img_mask (li

demo.py:119

↓ 1 callersFunctionprepare_input

( img_paths, img_mask, size, raymaps=None, raymap_mask=None, r

eval/video_depth/launch.py:200

↓ 1 callersFunctionprepare_input

( img_paths, img_mask, size, raymaps=None, raymap_mask=None, r

eval/relpose/launch.py:300

↓ 1 callersFunctionprepare_jobs

(pairs, num_levels, num_pairs_in_dir)

src/croco/datasets/crops/extract_crops_from_images.py:94

↓ 1 callersFunctionprepare_output

Process inference outputs to generate point clouds and camera parameters for visualization. Args: outputs (dict): Inference outputs.

demo.py:234

↓ 1 callersFunctionprepare_output

(outputs, revisit=1)

eval/video_depth/launch.py:296

↓ 1 callersFunctionprepare_output

(outputs, revisit=1, solve_pose=False)

eval/relpose/launch.py:396

↓ 1 callersFunctionprocess_bonn

(args, img_path)

eval/relpose/metadata.py:218

↓ 1 callersFunctionprocess_directory

(directory)

eval/relpose/evo_utils.py:436

↓ 1 callersFunctionprocess_kitti

(args, img_path)

eval/relpose/metadata.py:211

↓ 1 callersFunctionprocess_nyu

(args, img_path)

eval/video_depth/metadata.py:177

↓ 1 callersFunctionprocess_nyu

(args, img_path)

eval/relpose/metadata.py:236

↓ 1 callersFunctionprocess_scannet

(args, img_path)

eval/video_depth/metadata.py:183

↓ 1 callersFunctionprocess_sintel

(args, img_path)

eval/video_depth/metadata.py:191

↓ 1 callersFunctionprocess_sintel

(args, img_path)

eval/relpose/metadata.py:250

↓ 1 callersFunctionpts3d_to_trimesh

(img, pts3d, valid=None)

src/dust3r/viz.py:54

↓ 1 callersFunctionquaternion_conjugate

Compute the conjugate of quaternion q (w, x, y, z).

src/dust3r/utils/camera.py:423

↓ 1 callersFunctionquaternion_multiply

Multiply two quaternions q1 and q2.

src/dust3r/utils/camera.py:430

↓ 1 callersFunctionquaternion_to_matrix

Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten

src/dust3r/utils/camera.py:364

↓ 1 callersMethodrandom_sequence_no_revisit_with_backtracking

( adjacency_list, k, start_index, rng: np.random.Generator )

src/dust3r/datasets/blendedmvs.py:79

↓ 1 callersMethodrandom_sequence_with_optional_repeats

( adjacency_list, k, start_index, rng: np.random.Generator, max_k=None

src/dust3r/datasets/blendedmvs.py:127

↓ 1 callersFunctionravel_xy

(pos, shape)

eval/mv_recon/dataset_utils/corr.py:28

↓ 1 callersFunctionravel_xy

(pos, shape)

src/dust3r/datasets/utils/corr.py:31

↓ 1 callersMethodread_data

(self, pc_list, color_list, conf_list, edge_color_list=None)

viser_utils.py:752

↓ 1 callersMethodread_data

(self)

src/dust3r/viz.py:885

↓ 1 callersMethodread_h5_file

(self, h5_file_path)

src/dust3r/datasets/blendedmvs.py:33

↓ 1 callersFunctionreciprocal_1d

(corres_1_to_2, corres_2_to_1, ret_recip=False)

eval/mv_recon/dataset_utils/corr.py:43

↓ 1 callersFunctionreciprocal_1d

(corres_1_to_2, corres_2_to_1, ret_recip=False)

src/dust3r/datasets/utils/corr.py:46

↓ 1 callersFunctionrecover_cam_params

(pts3ds_self, pts3ds_other, conf_self, conf_other)

eval/relpose/launch.py:276

↓ 1 callersFunctionreg_desc

(desc, mode="norm")

src/dust3r/heads/postprocess.py:105

↓ 1 callersFunctionreproject

(pts3d, K, world2cam, shape)

eval/mv_recon/dataset_utils/corr.py:18

↓ 1 callersFunctionreproject

(pts3d, K, world2cam, shape)

src/dust3r/datasets/utils/corr.py:19

↓ 1 callersMethodreset

(self)

src/croco/stereoflow/criterion.py:243

↓ 1 callersFunctionrope_2d_cpu

src/croco/models/curope/curope.cpp:11

↓ 1 callersMethodrotate_half

(x)

src/croco/models/pos_embed.py:148

↓ 1 callersFunctionrotate_vector

Rotate vector v by quaternion q.

src/dust3r/utils/camera.py:443

↓ 1 callersFunctionrotation_matrix_to_quaternion

:param R: [3, 3] :return: [4]

src/dust3r/viz.py:847

↓ 1 callersFunctionrun

↓ 1 callersFunctionrun_inference

Execute the full inference and visualization pipeline. Args: args: Parsed command-line arguments.

demo.py:419

↓ 1 callersMethodsample_other_random_viewpoint

Sample a random viewpoint close to an existing one, using the navmesh and a reference observed point.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:271

↓ 1 callersFunctionsave_current_code

(outdir)

src/train.py:79

↓ 1 callersFunctionsave_depth_maps

(pts3ds_self, path, conf_self=None)

eval/video_depth/utils.py:53

↓ 1 callersFunctionsave_final_model

(accelerator, args, epoch, model_without_ddp, best_so_far=None)

src/train.py:337

↓ 1 callersFunctionsave_focals

(cam_dict, path)

eval/relpose/utils.py:90

↓ 1 callersFunctionsave_intrinsics

(cam_dict, path)

eval/relpose/utils.py:97

↓ 1 callersFunctionsave_on_master

(accelerator: Accelerator, *args, **kwargs)

src/croco/utils/misc.py:242

↓ 1 callersFunctionsave_trajectory_tum_format

(traj, filename)

eval/relpose/evo_utils.py:401

↓ 1 callersFunctionsave_tum_poses

(poses, path)

eval/relpose/utils.py:84

↓ 1 callersMethodset_color_border

(image, border_width=5, color=[1, 0, 0])

viser_utils.py:734

↓ 1 callersMethodset_downstream_head

( self, output_mode, head_type, landscape_only, depth_mode, co

src/dust3r/model.py:487

↓ 1 callersMethodset_epoch

(self, epoch)

src/dust3r/datasets/base/batched_sampler.py:44

↓ 1 callersMethodset_freeze

(self, freeze)

src/dust3r/model.py:429

↓ 1 callersFunctionsetup_for_distributed

This function disables printing when not in master process

src/train.py:62

↓ 1 callersFunctionshow_raw_pointcloud

(pts3d, colors, point_size=2)

src/dust3r/viz.py:45

↓ 1 callersFunctionsintel_cam_read

Read camera data, return (M,N) tuple. M is the intrinsic matrix, N is the extrinsic matrix, so that x = M*N*X, with x being a point in h

eval/relpose/evo_utils.py:19

↓ 1 callersMethodspatial_transform

(self, img1, img2, flow, dname)

src/croco/stereoflow/augmentor.py:334

↓ 1 callersFunctionstandardize_quaternion

Convert a unit quaternion to a standard form: one in which the real part is non negative. Args: quaternions: Quaternions with re

src/dust3r/utils/camera.py:329

↓ 1 callersFunctionstandardize_quaternion

Convert a unit quaternion to a standard form: one in which the real part is non negative. Args: quaternions: Quaternions with re

src/dust3r/heads/postprocess.py:154

↓ 1 callersMethodsubmission_save_pairname

(self, pairname, prediction, outdir, time)

src/croco/stereoflow/datasets_flow.py:508

↓ 1 callersFunctiontest_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, data_loader: Sized, accelerator: Acceler

src/train.py:556

↓ 1 callersFunctionto_gpu

(_view, device)

src/dust3r/utils/device.py:91

↓ 1 callersFunctionto_numpy

(x)

eval/relpose/utils.py:54

↓ 1 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

viser_utils.py:25

↓ 1 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

eval/relpose/utils.py:23

↓ 1 callersFunctiontrain

(args)

src/train.py:110

↓ 1 callersFunctiontrain_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, data_loader: Sized, optimizer: torch.opt

src/train.py:371

↓ 1 callersFunctiontrain_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, data_loader: Iterable, optimizer: torch.

src/croco/pretrain.py:311

↓ 1 callersFunctiontrain_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, metrics: torch.nn.Module, data_loader: I

src/croco/stereoflow/engine.py:26

↓ 1 callersFunctiontranspose_to_landscape

(view)

eval/mv_recon/base.py:255

↓ 1 callersFunctiontranspose_to_landscape

Predict in the correct aspect-ratio, then transpose the result in landscape and stack everything back together.

src/dust3r/utils/misc.py:55

↓ 1 callersFunctionvalidate_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, metrics: torch.nn.Module, data_loaders:

src/croco/stereoflow/engine.py:133

↓ 1 callersFunctionvis_and_cat

( gt_imgs, pred_imgs, cross_gt_depths, cross_pred_depths, self_gt_depths, self_pred_de

src/train.py:669

↓ 1 callersFunctionvis_disparity

(disp, m=None, M=None)

src/croco/stereoflow/datasets_stereo.py:964

← previous next →401–500 of 1,064, ranked by callers