Functions — github.com/cvg/NoPoSplat

hub / github.com/cvg/NoPoSplat / functions

Functions553 in github.com/cvg/NoPoSplat

⨍ Functions 553◇ Types & classes 135↳ Endpoints 1

↓ 2 callersFunctioncompute_equal_aabb_with_margin

( minima: Float[Tensor, "*#batch 3"], maxima: Float[Tensor, "*#batch 3"], margin: float = 0.1, )

src/visualization/drawing/cameras.py:153

↓ 2 callersMethodconvert_images

( self, images: list[UInt8[Tensor, "..."]], )

src/dataset/dataset_re10k.py:228

↓ 2 callersFunctionconvert_to_buffer

(module: nn.Module, persistent: bool = True)

src/misc/nn_module_tools.py:4

↓ 2 callersFunctioncreate_dpt_head

return PixelwiseTaskWithDPT for given net params

src/model/encoder/heads/dpt_head.py:101

↓ 2 callersFunctionextrinsics_to_pivot_parameters

Convert the extrinsics to a representation with 5 degrees of freedom: 1. Distance from pivot point in the "X" (look cross pivot axis) direction.

src/visualization/camera_trajectory/interpolation.py:107

↓ 2 callersFunctiongenerate_conversions

( shape: tuple[int, int], device: torch.device, x_range: Optional[Pair] = None, y_range: Optio

src/visualization/drawing/coordinate_conversion.py:19

↓ 2 callersFunctiongenerate_sample_grid

( shape: tuple[int, int], device: torch.device, )

src/visualization/drawing/rendering.py:18

↓ 2 callersFunctiongenerate_wobble

( extrinsics: Float[Tensor, "*#batch 4 4"], radius: Float[Tensor, "*#batch"], t: Float[Tensor, " t

src/visualization/camera_trajectory/wobble.py:26

↓ 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/model/encoder/backbone/croco/pos_embed.py:51

↓ 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/model/encoder/backbone/croco/pos_embed.py:22

↓ 2 callersFunctionget_backbone

(cfg: BackboneCfg, d_in: int = 3)

src/model/encoder/backbone/__init__.py:20

↓ 2 callersMethodget_conf_log

(self, x)

src/loss/loss_point.py:164

↓ 2 callersFunctionget_data_shim

Get functions that modify the batch. It's sometimes necessary to modify batches outside the data loader because GPU computations are required to m

src/dataset/data_module.py:17

↓ 2 callersFunctionget_decoder

(decoder_cfg: DecoderCfg)

src/model/decoder/__init__.py:11

↓ 2 callersFunctionget_encoder

(cfg: EncoderCfg)

src/model/encoder/__init__.py:16

↓ 2 callersFunctionget_fov

(intrinsics: Float[Tensor, "batch 3 3"])

src/geometry/projection.py:247

↓ 2 callersFunctionget_losses

(cfgs: list[LossCfgWrapper])

src/loss/__init__.py:15

↓ 2 callersMethodget_name

(self)

src/loss/loss_point.py:81

↓ 2 callersFunctionget_projection_matrix

Maps points in the viewing frustum to (-1, 1) on the X/Y axes and (0, 1) on the Z axis. Differs from the OpenGL version in that Z doesn't have ran

src/model/decoder/cuda_splatting.py:16

↓ 2 callersFunctionhomogenize_vectors

Convert batched vectors (xyz) to (xyz0).

src/geometry/projection.py:16

↓ 2 callersFunctionis_symmetrized

(gt1, gt2)

src/model/encoder/backbone/croco/misc.py:32

↓ 2 callersFunctionmake_batch_symmetric

(view1, view2)

src/model/encoder/backbone/croco/misc.py:66

↓ 2 callersMethodmap_pdf_to_opacity

( self, pdf: Float[Tensor, " *batch"], global_step: int, )

src/model/encoder/encoder_noposplat.py:118

↓ 2 callersMethodmap_pdf_to_opacity

( self, pdf: Float[Tensor, " *batch"], global_step: int, )

src/model/encoder/encoder_noposplat_multi.py:105

↓ 2 callersFunctionnormalize_pointcloud

renorm pointmaps pts1, pts2 with norm_mode

src/geometry/ptc_geometry.py:270

↓ 2 callersFunctionpostprocess

extract 3D points/confidence from prediction head output

src/model/encoder/heads/postprocess.py:10

↓ 2 callersFunctionproject_camera_space

( points: Float[Tensor, "*#batch dim"], intrinsics: Float[Tensor, "*#batch dim dim"], epsilon: flo

src/geometry/projection.py:47

↓ 2 callersFunctionproject_rays

( origins: Float[Tensor, "*#batch 3"], directions: Float[Tensor, "*#batch 3"], extrinsics: Float[T

src/geometry/epipolar_lines.py:157

↓ 2 callersFunctionrearrange_head

(feat, patch_size, H, W)

src/model/encoder/encoder_noposplat.py:54

↓ 2 callersFunctionreflect_views

(views: AnyViews)

src/dataset/shims/augmentation_shim.py:16

↓ 2 callersFunctionrender_over_image

( image: Float[Tensor, "3 height width"], color_function: ColorFunction, device: torch.device,

src/visualization/drawing/rendering.py:136

↓ 2 callersFunctionsanitize_pair

(pair: Pair, device: torch.device)

src/visualization/drawing/types.py:63

↓ 2 callersFunctionsave_chunk

()

src/scripts/convert_dl3dv.py:120

↓ 2 callersMethodschedule

(self, initial: int, final: int)

src/dataset/view_sampler/view_sampler_bounded.py:25

↓ 2 callersFunctionselout

(ar)

src/model/encoder/backbone/croco/misc.py:99

↓ 2 callersMethodshuffle

(self, lst: list)

src/dataset/dataset_re10k.py:87

↓ 2 callersFunctionskew_sym_mat

(x)

src/misc/cam_utils.py:54

↓ 2 callersFunctionssim

r""" interface of ssim Args: X (torch.Tensor): a batch of images, (N,C,H,W) Y (torch.Tensor): a batch of images, (N,C,H,W)

src/loss/loss_ssim.py:129

↓ 2 callersFunctiontrajectory_fn

(t)

src/visualization/video_render.py:43

↓ 2 callersFunctiontransform_rigid

Apply a rigid-body transformation to points or vectors.

src/geometry/projection.py:23

↓ 2 callersFunctiontransposed

(dic)

src/model/encoder/backbone/croco/misc.py:116

↓ 2 callersFunctionupdate_pose

(cam_trans_delta: Float[Tensor, "batch 3"], cam_rot_delta: Float[Tensor, "batch 3"],

src/misc/cam_utils.py:118

↓ 2 callersFunctionversion_to_int

Convert versions of the form vX to X. For example, v12 to 12.

src/misc/wandb_tools.py:6

↓ 1 callersFunctionSE3_exp

(tau)

src/misc/cam_utils.py:103

↓ 1 callersFunctionSO3_exp

(theta)

src/misc/cam_utils.py:67

↓ 1 callersFunctionV

(theta)

src/misc/cam_utils.py:85

↓ 1 callersMethod__init__

(self, net, has_conf=False)

src/model/encoder/heads/linear_head.py:50

↓ 1 callersMethod__init__

r""" class for ssim Args: data_range (float or int, optional): value range of input images. (usually 1.0 or 255) size_

src/loss/loss_ssim.py:275

↓ 1 callersMethod_decoder

(self, feat, pose, extra_embed=None)

src/model/encoder/backbone/backbone_croco_multiview.py:147

↓ 1 callersMethod_decoder

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

src/model/encoder/backbone/croco/croco.py:166

↓ 1 callersMethod_decoder

(self, f1, pos1, f2, pos2)

src/model/distiller/dust3d_backbone.py:128

↓ 1 callersMethod_encode_image

(self, image, true_shape, intrinsics_embed=None)

src/model/encoder/backbone/backbone_croco_multiview.py:123

↓ 1 callersMethod_gen_associated_legendre

r"""Computes associated Legendre functions (ALFs) of the first kind. The ALFs of the first kind are used in spherical harmonics. The spherica

src/misc/sht.py:1557

↓ 1 callersMethod_gen_recurrence_mask

Generates mask for recurrence relation on the remaining entries. The remaining entries are with respect to the diagonal and offdiagonal

src/misc/sht.py:1474

↓ 1 callersMethod_init_legendre

(self)

src/misc/sht.py:1538

↓ 1 callersMethod_init_weights

(self, m)

src/model/encoder/backbone/croco/croco.py:119

↓ 1 callersFunction_intersperse

(iterable: Iterable, delimiter: Any)

src/visualization/layout.py:44

↓ 1 callersFunction_ntuple

(n)

src/model/encoder/backbone/croco/blocks.py:24

↓ 1 callersMethod_recursive

(self, i: int, p_val: torch.Tensor, x: torch.Tensor)

src/misc/sht.py:1527

↓ 1 callersMethod_set_decoder

(self, enc_embed_dim, dec_embed_dim, dec_num_heads, dec_depth, mlp_ratio, norm_layer, norm_im2_in_dec)

src/model/encoder/backbone/croco/croco.py:95

↓ 1 callersMethod_set_mask_generator

(self, num_patches, mask_ratio)

src/model/encoder/backbone/croco/croco.py:89

↓ 1 callersMethod_set_mask_token

(self, dec_embed_dim)

src/model/encoder/backbone/croco/croco.py:92

↓ 1 callersMethod_set_patch_embed

(self, img_size=224, patch_size=16, enc_embed_dim=768)

src/model/encoder/backbone/croco/croco.py:86

↓ 1 callersMethod_set_prediction_head

(self, dec_embed_dim, patch_size)

src/model/encoder/backbone/croco/croco.py:107

↓ 1 callersFunctionadapt_input_conv

(in_chans, conv_weight)

src/misc/weight_modify.py:87

↓ 1 callersFunctionadapt_linear

(conv_weight)

src/misc/weight_modify.py:130

↓ 1 callersFunctionangle_error_mat

(R1, R2)

src/evaluation/metrics.py:70

↓ 1 callersFunctionangle_error_vec

(v1, v2)

src/evaluation/metrics.py:76

↓ 1 callersFunctionapply_augmentation_shim

Randomly augment the training images.

src/dataset/shims/augmentation_shim.py:24

↓ 1 callersFunctioncamera_normalization

(pivotal_pose: torch.Tensor, poses: torch.Tensor)

src/misc/cam_utils.py:27

↓ 1 callersFunctioncenter_crop

( images: Float[Tensor, "*#batch c h w"], intrinsics: Float[Tensor, "*#batch 3 3"], shape: tuple[i

src/dataset/shims/crop_shim.py:25

↓ 1 callersFunctioncheckpoint_filter_fn

convert patch embedding weight from manual patchify + linear proj to conv

src/misc/weight_modify.py:144

↓ 1 callersFunctioncolor_function

( xy: Float[Tensor, "point 2"], )

src/visualization/drawing/lines.py:42

↓ 1 callersFunctioncompute_aabb

Compute an axis-aligned bounding box for the camera frustums.

src/visualization/drawing/cameras.py:123

↓ 1 callersMethodcompute_loss

(self, *args, **kwargs)

src/loss/loss_point.py:78

↓ 1 callersFunctioncompute_pose_error

(pose_gt, pose_pred)

src/evaluation/metrics.py:88

↓ 1 callersFunctioncompute_translation_error

(t1, t2)

src/evaluation/metrics.py:83

↓ 1 callersFunctionconfidence_map

(result)

src/misc/utils.py:25

↓ 1 callersFunctionconstruct_list_of_attributes

(num_rest: int)

src/model/ply_export.py:12

↓ 1 callersMethodconvert_images

( self, images, )

src/dataset/dataset_scannet_pose.py:231

↓ 1 callersMethodconvert_poses

( self, poses: Float[Tensor, "batch 18"], )

src/dataset/dataset_re10k.py:205

↓ 1 callersFunctioncreate_gs_dpt_head

return PixelwiseTaskWithDPT for given net params

src/model/encoder/heads/dpt_gs_head.py:188

↓ 1 callersFunctioncyan

(text: str)

src/main.py:36

↓ 1 callersFunctiondepthmap_to_camera_coordinates

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

src/geometry/ptc_geometry.py:166

↓ 1 callersFunctiondepthmap_to_pts3d

Args: - depthmap (BxHxW array): - pseudo_focal: [B,H,W] ; [B,2,H,W] or [B,1,H,W] Returns: pointmap of absolute coordi

src/geometry/ptc_geometry.py:115

↓ 1 callersFunctiondetect_msaa_pixels

( image: Float[Tensor, "batch 4 height width"], )

src/visualization/drawing/rendering.py:29

↓ 1 callersMethoddistance

(self, a, b)

src/loss/loss_point.py:55

↓ 1 callersFunctiondownload_checkpoint

( run_id: str, download_dir: Path, version: str | None, )

src/misc/wandb_tools.py:11

↓ 1 callersFunctiondraw_cameras

( resolution: int, extrinsics: Float[Tensor, "batch 4 4"], intrinsics: Float[Tensor, "batch 3 3"],

src/visualization/drawing/cameras.py:14

↓ 1 callersFunctiondraw_label

Draw a black label on a white background with no border.

src/visualization/annotation.py:16

↓ 1 callersFunctiondrop_path

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

src/model/encoder/backbone/croco/blocks.py:32

↓ 1 callersMethoddump_memory

(self, path: Path)

src/misc/benchmarker.py:30

↓ 1 callersFunctioneuler_to_matrix

( rotations: Float[Tensor, "*batch 3"], pattern: str, )

src/visualization/camera_trajectory/interpolation.py:96

↓ 1 callersFunctionevaluate

(cfg_dict: DictConfig)

src/eval_pose.py:45

↓ 1 callersFunctionevaluate

(cfg_dict: DictConfig)

src/scripts/compute_metrics.py:36

↓ 1 callersFunctionexport_ply

( means: Float[Tensor, "gaussian 3"], scales: Float[Tensor, "gaussian 3"], rotations: Float[Tensor

src/model/ply_export.py:26

↓ 1 callersMethodforward

(self, x)

src/model/encoder/backbone/croco/blocks.py:73

↓ 1 callersMethodforward

(self, context: dict, symmetrize_batch=False, return_views=Fal

src/model/distiller/dust3d_backbone.py:170

↓ 1 callersFunctiongenerate_heterogeneous_index

Generate indices for all pairs except self-pairs.

src/misc/heterogeneous_pairings.py:9

↓ 1 callersFunctiongenerate_rotation_coordinate_frame

Generate a coordinate frame where the Y direction is normal to the plane defined by unit vectors a and b. The other axes are arbitrary.

src/visualization/camera_trajectory/interpolation.py:64

← previous next →101–200 of 553, ranked by callers