Functions — github.com/cvlab-kaist/PF3plat

hub / github.com/cvlab-kaist/PF3plat / functions

Functions843 in github.com/cvlab-kaist/PF3plat

⨍ Functions 843◇ Types & classes 197↳ Endpoints 2

↓ 2 callersFunction_compare_projections

( intersections: Iterable[PointProjection], reduction: Literal["min", "max"], )

src/geometry/epipolar_lines.py:107

↓ 2 callersFunction_compute_offset

(base: int, overlay: int, align: Alignment)

src/visualization/layout.py:66

↓ 2 callersFunction_get_cross_dim

(main_axis: Axis)

src/visualization/layout.py:59

↓ 2 callersFunction_get_main_dim

(main_axis: Axis)

src/visualization/layout.py:52

↓ 2 callersFunction_is_in_bounds

Check whether the specified XY coordinates are within the normalized image plane, which has a range from 0 to 1 in each direction.

src/geometry/epipolar_lines.py:19

↓ 2 callersFunction_is_in_front_of_camera

Check whether the specified points in camera space are in front of the camera.

src/geometry/epipolar_lines.py:29

↓ 2 callersFunction_is_positive_t

Check whether the specified t value is positive.

src/geometry/epipolar_lines.py:37

↓ 2 callersFunction_preprocess

(rgbs, intrinsics, shapes, ratio)

src/model/unidepth/unidepthv2/unidepthv2.py:95

↓ 2 callersFunction_sanitize_color

(color: Color)

src/visualization/layout.py:30

↓ 2 callersFunction_shapes

(image_shape, shape_constraints)

src/model/unidepth/unidepthv2/unidepthv2.py:78

↓ 2 callersFunctionapply_cached_rotary_emb

(freqs: torch.Tensor, t: torch.Tensor)

src/model/LightGlue/lightglue/lightglue.py:57

↓ 2 callersFunctionapply_color_map

( x: Float[Tensor, " *batch"], color_map: str = "inferno", )

src/visualization/color_map.py:9

↓ 2 callersFunctionapply_crop_shim_to_views

(views: AnyViews, shape: tuple[int, int])

src/dataset/shims/crop_shim.py:78

↓ 2 callersFunctionapply_patch_shim_to_views

(views: BatchedViews, patch_size: int)

src/dataset/shims/patch_shim.py:4

↓ 2 callersFunctionbatch_features

(features)

src/model/encoder/multiview_transformer.py:490

↓ 2 callersFunctionbroadcat

(tensors, dim=-1)

src/model/unidepth/utils/positional_embedding.py:88

↓ 2 callersFunctionbroadcat

(tensors, dim=-1)

src/model/unidepth/layers/positional_encoding.py:104

↓ 2 callersFunctioncamera_chaining

Synchronizes cameras by chaining adjacent views: P_{0, 3} = P_{2, 3} @ P_{1, 2} @ P_{0, 1} Args: Ps (dict): Pairwise view estimat

src/flow_util.py:341

↓ 2 callersFunctioncat

Arrange images in a line. The interface resembles a CSS div with flexbox.

src/visualization/layout.py:109

↓ 2 callersFunctioncompute_depth_for_disparity

Compute the depth at which moving the maximum distance between cameras corresponds to the specified disparity (in pixels).

src/dataset/shims/bounds_shim.py:9

↓ 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:243

↓ 2 callersMethodconvert_images

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

src/dataset/dataset_dl3dv.py:246

↓ 2 callersMethodconvert_images

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

src/dataset/dataset_dl3dv_test.py:249

↓ 2 callersFunctioncount_flops_attn

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

src/model/encoder/costvolume/ldm_unet/unet.py:507

↓ 2 callersFunctiondelta

(tensor1, tensor2, exponent)

src/model/unidepth/utils/evaluation_depth.py:48

↓ 2 callersMethoddevice

(self)

src/model/unidepth/unidepthv2/unidepthv2.py:340

↓ 2 callersFunctiondrop_add_residual_stochastic_depth

( x: torch.Tensor, residual_func: Callable[[torch.Tensor], torch.Tensor], sample_drop_ratio: float

src/model/unidepth/backbones/metadinov2/block.py:112

↓ 2 callersFunctiondrop_add_residual_stochastic_depth_list

( x_list: List[torch.Tensor], residual_func: Callable[[torch.Tensor, Any], torch.Tensor], sample_d

src/model/unidepth/backbones/metadinov2/block.py:197

↓ 2 callersMethoddump_memory

(self, path: Path)

src/misc/benchmarker.py:30

↓ 2 callersFunctionexists

(val)

src/model/encoder/costvolume/ldm_unet/attention.py:9

↓ 2 callersFunctionexists

(val)

src/model/unidepth/utils/misc.py:170

↓ 2 callersMethodextract_single_image

(self, image: torch.Tensor)

src/model/LightGlue/lightglue/sift.py:140

↓ 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 callersFunctionfrom_homogeneous

Remove the homogeneous dimension of N-dimensional points. Args: points: torch.Tensor or numpy.ndarray with size (..., N+1). Returns:

src/flow_util.py:187

↓ 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_fourier_features

( x: torch.Tensor, dim: int = 512, max_freq: int = 64, use_cos: bool = False, use_log: boo

src/model/unidepth/utils/positional_embedding.py:219

↓ 2 callersFunctiongenerate_sample_grid

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

src/visualization/drawing/rendering.py:18

↓ 2 callersFunctiongenerate_wobble_transformation

( radius: Float[Tensor, "*#batch"], t: Float[Tensor, " time_step"], num_rotations: int = 1, sc

src/visualization/camera_trajectory/wobble.py:8

↓ 2 callersFunctionget_1d_sincos_pos_embed_from_grid

This function generates a 1D positional embedding from a given grid using sine and cosine functions. Args: - embed_dim: The embedding di

src/flow_util.py:227

↓ 2 callersFunctionget_attn_bias_and_cat

this will perform the index select, cat the tensors, and provide the attn_bias from cache

src/model/unidepth/backbones/metadinov2/block.py:167

↓ 2 callersFunctionget_decoder

(decoder_cfg: DecoderCfg, dataset_cfg: DatasetCfg)

src/model/decoder/__init__.py:12

↓ 2 callersFunctionget_losses

(cfgs: list[LossCfgWrapper])

src/loss/__init__.py:16

↓ 2 callersMethodget_matchability

(self, desc: torch.Tensor)

src/model/LightGlue/lightglue/lightglue.py:292

↓ 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:17

↓ 2 callersMethodget_pruning_mask

mask points which should be removed

src/model/LightGlue/lightglue/lightglue.py:631

↓ 2 callersFunctionget_relative_Rt

Generates the relative Rt assuming that we have two world to camera Rts. Hence, Rt_ij = inverse(Rt_i) @ Rt_j. Args: Rt_i (FloatTensor

src/loss/loss_pose.py:141

↓ 2 callersFunctionhomogenize_vectors

Convert batched vectors (xyz) to (xyz0).

src/geometry/projection.py:16

↓ 2 callersFunctioninterpolate_extrinsics

Interpolate extrinsics by rotating around their "focus point," which is the least-squares intersection between the look vectors of the initial and

src/visualization/camera_trajectory/interpolation.py:208

↓ 2 callersFunctioninterpolate_intrinsics

( initial: Float[Tensor, "*#batch 3 3"], final: Float[Tensor, "*#batch 3 3"], t: Float[Tensor, " t

src/visualization/camera_trajectory/interpolation.py:8

↓ 2 callersFunctionis_dist_avail_and_initialized

()

src/model/unidepth/utils/distributed.py:19

↓ 2 callersFunctionlist_knn_gather

(xs, idxs)

src/flow_util.py:915

↓ 2 callersFunctionload_typed_root_config

(cfg: DictConfig)

src/config.py:85

↓ 2 callersFunctionmake_2tuple

(x)

src/model/unidepth/backbones/metadinov2/patch_embed.py:17

↓ 2 callersFunctionmake_Rt

Encode the transformation X -> X @ R + t where X has shape [n,3]

src/flow_util.py:1006

↓ 2 callersFunctionmeasure

(matcher, data, device="cuda", r=100)

src/model/LightGlue/benchmark.py:18

↓ 2 callersMethodno_weight_decay_keywords

(self)

src/model/unidepth/unidepthv2/decoder.py:528

↓ 2 callersFunctionnormalize_keypoints

( kpts: torch.Tensor, size: Optional[torch.Tensor] = None )

src/model/LightGlue/lightglue/lightglue.py:25

↓ 2 callersMethodpad

(self, x: torch.Tensor)

src/model/LightGlue/lightglue/aliked.py:279

↓ 2 callersFunctionproject_camera_space

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

src/geometry/projection.py:47

↓ 2 callersMethodproject_rays

(self, rays, shapes)

src/model/unidepth/unidepthv2/decoder.py:251

↓ 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 callersFunctionrotate_half

(x)

src/model/unidepth/utils/positional_embedding.py:107

↓ 2 callersFunctionrotate_half

(x)

src/model/unidepth/layers/positional_encoding.py:123

↓ 2 callersFunctionsanitize_pair

(pair: Pair, device: torch.device)

src/visualization/drawing/types.py:61

↓ 2 callersMethodschedule

(self, initial: int, final: int)

src/dataset/view_sampler/view_sampler_bounded.py:25

↓ 2 callersMethodset_original_shapes

(self, shapes: tuple[int, int])

src/model/unidepth/unidepthv2/decoder.py:233

↓ 2 callersMethodshuffle

(self, lst: list)

src/dataset/dataset_re10k.py:98

↓ 2 callersMethodshuffle

(self, lst: list)

src/dataset/dataset_dl3dv.py:99

↓ 2 callersMethodshuffle

(self, lst: list)

src/dataset/dataset_dl3dv_test.py:102

↓ 2 callersFunctionsingle_head_split_window_attention

(q, k, v, num_splits=1, with_shi

src/model/encoder/multiview_transformer.py:98

↓ 2 callersFunctionspherical_zbuffer_to_euclidean

(spherical_tensor)

src/model/unidepth/utils/geometric.py:54

↓ 2 callersMethodstate_dict

r"""Returns the state of the ExponentialMovingAverage as a dict.

src/model/unidepth/utils/ema_torch.py:275

↓ 2 callersMethodtime

(self, tag: str, num_calls: int = 1)

src/misc/benchmarker.py:16

↓ 2 callersFunctionto_homogeneous

Convert N-dimensional points to homogeneous coordinates. Args: points: torch.Tensor or numpy.ndarray with size (..., N). Returns:

src/flow_util.py:145

↓ 2 callersFunctiontransform_points_Rt

( points: torch.Tensor, viewpoint: torch.Tensor, inverse: bool = False )

src/loss/loss_pose.py:131

↓ 2 callersFunctiontransform_rigid

Apply a rigid-body transformation to points or vectors.

src/geometry/projection.py:23

↓ 2 callersMethodunpad

(self, x: torch.Tensor)

src/model/LightGlue/lightglue/aliked.py:283

↓ 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_inverse

(P)

src/flow_util.py:321

↓ 1 callersMethod__init__

( self, in_features: int, hidden_features: Optional[int] = None, out_features:

src/model/unidepth/backbones/metadinov2/swiglu_ffn.py:14

↓ 1 callersMethod__init__

(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)

src/model/unidepth/layers/mlp.py:11

↓ 1 callersMethod__init__

(self, **conf)

src/model/LightGlue/lightglue/utils.py:132

↓ 1 callersFunction_build_mlp

( nlayers, in_dim, bottleneck_dim, hidden_dim=None, use_bn=False, bias=True )

src/model/unidepth/backbones/metadinov2/dino_head.py:52

↓ 1 callersFunction_check_ratio

(image_ratio, ratio_bounds)

src/model/unidepth/unidepthv2/unidepthv2.py:33

↓ 1 callersFunction_check_resolution

(shape_constraints, resolution_level)

src/model/unidepth/unidepthv2/unidepthv2.py:45

↓ 1 callersMethod_forward

(self, x, y=None)

src/model/encoder/costvolume/ldm_unet/unet.py:446

↓ 1 callersMethod_forward

(self, data: dict)

src/model/LightGlue/lightglue/lightglue.py:477

↓ 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/model/unidepth/utils/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/model/unidepth/utils/sht.py:1474

↓ 1 callersFunction_get_closes_num_pixels

(image_shape, pixels_bounds)

src/model/unidepth/unidepthv2/unidepthv2.py:70

↓ 1 callersMethod_init_legendre

(self)

src/model/unidepth/utils/sht.py:1538

↓ 1 callersFunction_intersperse

(iterable: Iterable, delimiter: Any)

src/visualization/layout.py:44

↓ 1 callersFunction_make_dinov2_model_name

(arch_name: str, patch_size: int)

src/model/unidepth/backbones/dinov2.py:402

↓ 1 callersFunction_postprocess

(outs, ratio, original_shapes, mode="nearest-exact")

src/model/unidepth/unidepthv2/unidepthv2.py:107

↓ 1 callersMethod_recursive

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

src/model/unidepth/utils/sht.py:1527

↓ 1 callersMethod_reset_parameters

(self)

src/model/encoder/aggregation.py:153

↓ 1 callersFunction_ssim

(img1, img2, window, window_size, channel, size_average=True)

src/loss/loss_multissim.py:64

↓ 1 callersFunctionadd_residual

(x, brange, residual, residual_scale_factor, scaling_vector=None)

src/model/unidepth/backbones/metadinov2/block.py:146

← previous next →101–200 of 843, ranked by callers