Functions — github.com/cvg/NoPoSplat

hub / github.com/cvg/NoPoSplat / functions

Functions553 in github.com/cvg/NoPoSplat

⨍ Functions 553◇ Types & classes 135↳ Endpoints 1

↓ 36 callersFunctionadd_label

( image: Float[Tensor, "3 width height"], label: str, font: Path = Path("assets/Inter-Regular.otf"

src/visualization/annotation.py:38

↓ 24 callersFunctionhcat

Shorthand for a horizontal linear concatenation.

src/visualization/layout.py:149

↓ 24 callersFunctionvcat

Shorthand for a horizontal linear concatenation.

src/visualization/layout.py:171

↓ 19 callersFunctionadd_border

( image: Float[Tensor, "channel height width"], border: int = 8, color: Color = 1, )

src/visualization/layout.py:193

↓ 14 callersFunctionhead_factory

build a prediction head for the decoder

src/model/encoder/heads/__init__.py:12

↓ 12 callersMethoddevice

(self)

src/misc/sht.py:1436

↓ 12 callersFunctiondraw_points

( image: Float[Tensor, "3 height width"], points: Vector, color: Vector = [1, 1, 1], radius: S

src/visualization/drawing/points.py:13

↓ 9 callersFunctiondraw_lines

( image: Float[Tensor, "3 height width"], start: Vector, end: Vector, color: Vector, width

src/visualization/drawing/lines.py:13

↓ 8 callersMethodforward

( self, context: BatchedViews, )

src/model/encoder/encoder.py:20

↓ 7 callersFunctionget_distinct_color

(index: int)

src/visualization/colors.py:30

↓ 6 callersMethod__init__

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

src/model/encoder/backbone/croco/blocks.py:60

↓ 6 callersMethoddump

(self, path: Path)

src/misc/benchmarker.py:25

↓ 6 callersFunctioninvalid_to_nans

(arr, valid_mask, ndim=999)

src/model/encoder/backbone/croco/misc.py:120

↓ 6 callersFunctionprep_image

(image: FloatImage)

src/misc/image_io.py:38

↓ 6 callersFunctionproject

(points: Float[Tensor, "*batch 3"])

src/visualization/drawing/cameras.py:52

↓ 6 callersFunctiontranspose_to_landscape

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

src/model/encoder/backbone/croco/misc.py:71

↓ 5 callersFunctionapply_color_map_to_image

( image: Float[Tensor, "*batch height width"], color_map: str = "inferno", )

src/visualization/color_map.py:22

↓ 5 callersFunctionbox

( image: Float[Tensor, "3 height width"], )

src/model/encoder/visualization/encoder_visualizer_epipolar.py:25

↓ 5 callersFunctiongaussian_filter

r""" Blur input with 1-D kernel Args: input (torch.Tensor): a batch of tensors to be blurred window (torch.Tensor): 1-D gauss kern

src/loss/loss_ssim.py:29

↓ 5 callersFunctionget_world_rays

( coordinates: Float[Tensor, "*#batch dim"], extrinsics: Float[Tensor, "*#batch dim+2 dim+2"], int

src/geometry/projection.py:91

↓ 5 callersFunctionload_typed_config

( cfg: DictConfig, data_class: Type[T], extra_type_hooks: dict = {}, )

src/config.py:62

↓ 5 callersFunctionsample_image_grid

Get normalized (range 0 to 1) coordinates and integer indices for an image.

src/geometry/projection.py:131

↓ 5 callersFunctionsanitize_scalar

(scalar: Scalar, device: torch.device)

src/visualization/drawing/types.py:46

↓ 5 callersFunctionsanitize_vector

( vector: Vector, dim: int, device: torch.device, )

src/visualization/drawing/types.py:20

↓ 5 callersFunctionunproject_frustum_corners

( extrinsics: Float[Tensor, "batch 4 4"], intrinsics: Float[Tensor, "batch 3 3"], depth: Float[Ten

src/visualization/drawing/cameras.py:168

↓ 5 callersFunctionvis_depth_map

(result)

src/misc/utils.py:13

↓ 4 callersMethod__init__

(self, reduction='mean')

src/loss/loss_point.py:39

↓ 4 callersFunction_compute_point_projection

( xyz: Float[Tensor, "*#batch 3"], t: Float[Tensor, "*#batch"], intrinsics: Float[Tensor, "*#batch

src/geometry/epipolar_lines.py:134

↓ 4 callersFunction_fspecial_gauss_1d

r"""Create 1-D gauss kernel Args: size (int): the size of gauss kernel sigma (float): sigma of normal distribution Returns:

src/loss/loss_ssim.py:12

↓ 4 callersFunction_intersect_image_coordinate

Compute the intersection of the projection of a camera-space ray with a line that's parallel to the image frame, either horizontally or vertically

src/geometry/epipolar_lines.py:55

↓ 4 callersFunctioncompute_psnr

( ground_truth: Float[Tensor, "batch channel height width"], predicted: Float[Tensor, "batch channel h

src/evaluation/metrics.py:12

↓ 4 callersMethoddata_shim

(batch: BatchedExample)

src/model/encoder/encoder_noposplat.py:243

↓ 4 callersMethodforward

( self, prediction: DecoderOutput, batch: BatchedExample, gaussians: Gaussians

src/loss/loss.py:29

↓ 4 callersMethodget_bound

( self, bound: Literal["near", "far"], num_views: int, )

src/dataset/dataset_scannet_pose.py:241

↓ 4 callersMethodget_bound

( self, bound: Literal["near", "far"], num_views: int, )

src/dataset/dataset_re10k.py:238

↓ 4 callersFunctioninterleave

(tensor1, tensor2)

src/model/encoder/backbone/croco/misc.py:48

↓ 4 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

↓ 4 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

↓ 4 callersMethodload_state_dict

(self, ckpt, **kw)

src/model/distiller/dust3d_backbone.py:47

↓ 4 callersMethodlog_image

( self, key: str, images: list[Any], step: Optional[int] = None, **kwa

src/misc/LocalLogger.py:35

↓ 4 callersFunctionmake_fusion_block

(features, use_bn, width_ratio=1, expand=False)

src/model/encoder/heads/dpt_block.py:220

↓ 4 callersFunctionprocess_vector

(vector)

src/geometry/projection.py:250

↓ 4 callersFunctionsave_image

Save an image. Assumed to be in range 0-1.

src/misc/image_io.py:57

↓ 3 callersMethod__init__

Init. Args: scale_factor (float): scaling mode (str): interpolation mode

src/model/encoder/heads/dpt_block.py:234

↓ 3 callersMethod_encode_image

(self, image, true_shape, intrinsics_embed=None)

src/model/encoder/backbone/backbone_croco.py:132

↓ 3 callersMethod_encode_image

(self, image, true_shape)

src/model/distiller/dust3d_backbone.py:84

↓ 3 callersMethodadapt_tokens

(self, encoder_tokens)

src/model/encoder/heads/dpt_block.py:421

↓ 3 callersFunctioncompute_lpips

( ground_truth: Float[Tensor, "batch channel height width"], predicted: Float[Tensor, "batch channel h

src/evaluation/metrics.py:28

↓ 3 callersFunctioncompute_ssim

( ground_truth: Float[Tensor, "batch channel height width"], predicted: Float[Tensor, "batch channel h

src/evaluation/metrics.py:37

↓ 3 callersFunctionfill_default_args

(kwargs, func)

src/model/encoder/backbone/croco/misc.py:10

↓ 3 callersFunctionfreeze_all_params

(modules)

src/model/encoder/backbone/croco/misc.py:22

↓ 3 callersFunctiongenerate_coordinate_frame

Generate a coordinate frame given perpendicular, unit-length Y and Z vectors.

src/visualization/camera_trajectory/interpolation.py:55

↓ 3 callersFunctiongenerate_wobble_transformation

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

src/visualization/camera_trajectory/wobble.py:8

↓ 3 callersFunctionget_cfg

()

src/global_cfg.py:8

↓ 3 callersFunctionget_dataset

( cfgs: list[DatasetCfgWrapper], stage: Stage, step_tracker: StepTracker | None, )

src/dataset/__init__.py:24

↓ 3 callersMethodget_generator

(self, loader_cfg: DataLoaderStageCfg)

src/dataset/data_module.py:83

↓ 3 callersFunctionget_intrinsic_embedding

(context, degree=0, downsample=1, merge_hw=False)

src/geometry/camera_emb.py:7

↓ 3 callersFunctionget_overlap_tag

(overlap)

src/misc/utils.py:38

↓ 3 callersFunctionget_patch_embed

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

src/model/encoder/backbone/croco/patch_embed.py:13

↓ 3 callersMethodget_persistent

(self, loader_cfg: DataLoaderStageCfg)

src/dataset/data_module.py:80

↓ 3 callersFunctionhomogenize_points

Convert batched points (xyz) to (xyz1).

src/geometry/projection.py:9

↓ 3 callersFunctioninvalid_to_zeros

(arr, valid_mask, ndim=999)

src/model/encoder/backbone/croco/misc.py:129

↓ 3 callersFunctioninverse_normalize

(tensor, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))

src/misc/utils.py:6

↓ 3 callersFunctionpose_auc

(errors, thresholds)

src/misc/cam_utils.py:181

↓ 3 callersFunctionrender_video_generic

( gaussians: Gaussians, decoder: Decoder, batch: BatchedExample, trajectory_fn

src/visualization/video_render.py:126

↓ 3 callersMethodrender_video_generic

( self, batch: BatchedExample, trajectory_fn: TrajectoryFn, name: str,

src/model/model_wrapper.py:576

↓ 3 callersFunctionset_cfg

(new_cfg: DictConfig)

src/global_cfg.py:13

↓ 3 callersMethodtime

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

src/misc/benchmarker.py:16

↓ 3 callersFunctionunproject

Unproject 2D camera coordinates with the given Z values.

src/geometry/projection.py:74

↓ 2 callersMethod__init__

(self, in_planes, planes, norm_fn='group', stride=1)

src/model/encoder/heads/head_modules.py:7

↓ 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 callersMethod_decoder

(self, f1, pos1, f2, pos2, extra_embed1=None, extra_embed2=None)

src/model/encoder/backbone/backbone_croco.py:190

↓ 2 callersMethod_downstream_head

(self, head_num, decout, img_shape, ray_embedding=None)

src/model/encoder/encoder_noposplat.py:133

↓ 2 callersMethod_downstream_head

(self, head_num, decout, img_shape, ray_embedding=None)

src/model/encoder/encoder_noposplat_multi.py:120

↓ 2 callersMethod_downstream_head

(self, head_num, decout, img_shape)

src/model/distiller/dust3d_backbone.py:149

↓ 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 feat

src/model/encoder/backbone/croco/croco.py:129

↓ 2 callersMethod_encode_image_pairs

(self, img1, img2, true_shape1, true_shape2, intrinsics_embed1=None, intrinsics_embed2=None)

src/model/encoder/backbone/backbone_croco.py:156

↓ 2 callersMethod_encode_image_pairs

(self, img1, img2, true_shape1, true_shape2)

src/model/distiller/dust3d_backbone.py:98

↓ 2 callersMethod_encode_symmetrized

(self, view1, view2, force_asym=False)

src/model/encoder/backbone/backbone_croco.py:168

↓ 2 callersMethod_encode_symmetrized

(self, view1, view2, force_asym=False)

src/model/distiller/dust3d_backbone.py:109

↓ 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_interleave_imgs

(img1, img2)

src/model/encoder/backbone/croco/misc.py:54

↓ 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_sanitize_color

(color: Color)

src/visualization/layout.py:30

↓ 2 callersFunction_ssim

r""" Calculate ssim index for X and Y Args: X (torch.Tensor): images Y (torch.Tensor): images data_range (float or int):

src/loss/loss_ssim.py:58

↓ 2 callersFunctionadd_addtional_context_index

( indices: Int[Tensor, "*batch 2"], number_of_context_views: int, )

src/dataset/view_sampler/additional_view_hack.py:6

↓ 2 callersFunctionapply_color_map

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

src/visualization/color_map.py:9

↓ 2 callersFunctionapply_crop_shim

Crop images in the example.

src/dataset/shims/crop_shim.py:87

↓ 2 callersFunctionapply_crop_shim_to_views

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

src/dataset/shims/crop_shim.py:78

↓ 2 callersFunctionapply_normalize_shim

( batch: BatchedExample, mean: tuple[float, float, float] = (0.5, 0.5, 0.5), std: tuple[float, flo

src/dataset/shims/normalize_shim.py:21

↓ 2 callersFunctionapply_patch_shim_to_views

(views: BatchedViews, patch_size: int)

src/dataset/shims/patch_shim.py:4

↓ 2 callersMethodapply_rope1d

(self, tokens, pos1d, cos, sin)

src/model/encoder/backbone/croco/pos_embed.py:136

↓ 2 callersMethodbackward

(ctx, grad_res)

src/model/encoder/backbone/croco/curope/curope2d.py:25

↓ 2 callersFunctionbuild_covariance

( scale: Float[Tensor, "*#batch 3"], rotation_xyzw: Float[Tensor, "*#batch 4"], )

src/model/encoder/common/gaussians.py:33

↓ 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

next →1–100 of 553, ranked by callers