Functions — github.com/cvg/NoPoSplat

CodeHub MCPcopy Create free account

hub / github.com/cvg/NoPoSplat / functions

Functions553 in github.com/cvg/NoPoSplat

⨍ Functions 553◇ Types & classes 135↳ Endpoints 1

↓ 1 callersFunctiongeotrf

Apply a geometric transformation to a list of 3-D points. H: 3x3 or 4x4 projection matrix (typically a Homography) p: numpy/torch/tuple of c

src/geometry/ptc_geometry.py:41

↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid

(embed_dim, grid)

src/model/encoder/backbone/croco/pos_embed.py:40

↓ 1 callersMethodget_cos_sin

(self, D, seq_len, device, dtype)

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

↓ 1 callersMethodget_data_shim

The default shim doesn't modify the batch.

src/model/encoder/encoder.py:26

↓ 1 callersFunctionget_distiller

src/model/distiller/__init__.py:9

↓ 1 callersFunctionget_example_keys

(stage: Literal["test", "train"])

src/scripts/convert_dl3dv.py:22

↓ 1 callersFunctionget_local_rays

( coordinates: Float[Tensor, "*#batch dim"], intrinsics: Float[Tensor, "*#batch dim+1 dim+1"], )

src/geometry/projection.py:117

↓ 1 callersFunctionget_lpips

(device: torch.device)

src/evaluation/metrics.py:23

↓ 1 callersFunctionget_pnp_pose

(pts3d, opacity, K, H, W, opacity_threshold=0.3)

src/misc/cam_utils.py:158

↓ 1 callersFunctionget_resize_mat

(_old_size, _new_size)

src/misc/weight_modify.py:64

↓ 1 callersMethodget_scale_multiplier

( self, intrinsics: Float[Tensor, "*#batch 3 3"], pixel_size: Float[Tensor, "*#batch 2

src/model/encoder/common/gaussian_adapter.py:100

↓ 1 callersFunctionget_size

Get file or folder size in bytes.

src/scripts/convert_dl3dv.py:39

↓ 1 callersMethodget_step

src/misc/step_tracker.py:21

↓ 1 callersFunctionget_view_sampler

( cfg: ViewSamplerCfg, stage: Stage, overfit: bool, cameras_are_circular: bool, step_track

src/dataset/view_sampler/__init__.py:26

↓ 1 callersMethodindex

src/dataset/dataset_re10k.py:255

↓ 1 callersMethodinit

(self, dim_tokens_enc=768)

src/model/encoder/heads/dpt_head.py:27

↓ 1 callersMethodinit

(self, dim_tokens_enc=768)

src/model/encoder/heads/dpt_gs_head.py:104

↓ 1 callersMethodinit

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

src/model/encoder/heads/dpt_block.py:350

↓ 1 callersMethodinitialize_weights

src/model/encoder/backbone/croco/croco.py:111

↓ 1 callersFunctioninterpolate_circular

( a: Float[Tensor, "*#batch"], b: Float[Tensor, "*#batch"], t: Float[Tensor, "*#batch"], )

src/visualization/camera_trajectory/interpolation.py:162

↓ 1 callersFunctioninterpolate_pivot_parameters

( initial: Float[Tensor, "*#batch 5"], final: Float[Tensor, "*#batch 5"], t: Float[Tensor, " time_

src/visualization/camera_trajectory/interpolation.py:190

↓ 1 callersFunctionintersect_rays

Compute the least-squares intersection of rays. Uses the math from here: https://math.stackexchange.com/a/1762491/286022

src/visualization/camera_trajectory/interpolation.py:19

↓ 1 callersFunctionintersect_rays

Compute the least-squares intersection of rays. Uses the math from here: https://math.stackexchange.com/a/1762491/286022

src/geometry/projection.py:190

↓ 1 callersFunctioninv

Invert a torch or numpy matrix

src/misc/cam_utils.py:148

↓ 1 callersFunctionlift_to_3d

Calculate the 3D positions that correspond to the specified 2D points on the epipolar lines defined by the origins and directions. The extrinsics

src/geometry/epipolar_lines.py:264

↓ 1 callersFunctionload_image

( path: Union[Path, str], )

src/misc/image_io.py:71

↓ 1 callersFunctionload_images

Load JPG images as raw bytes (do not decode).

src/scripts/convert_dl3dv.py:48

↓ 1 callersFunctionload_metadata

(file_path: Path)

src/scripts/convert_dl3dv.py:74

↓ 1 callersFunctionload_raw

src/scripts/convert_dl3dv.py:44

↓ 1 callersFunctionload_typed_root_config

(cfg: DictConfig)

src/config.py:98

↓ 1 callersFunctionmake_scratch

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

src/model/encoder/heads/dpt_block.py:20

↓ 1 callersFunctionmatrix_to_euler

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

src/visualization/camera_trajectory/interpolation.py:85

↓ 1 callersFunctionms_ssim

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

src/loss/loss_ssim.py:192

↓ 1 callersFunctionnormalize

(a: Float[Tensor, "*#batch dim"])

src/visualization/camera_trajectory/interpolation.py:51

↓ 1 callersFunctionnormalize_image

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

src/dataset/shims/normalize_shim.py:15

↓ 1 callersFunctionopengl_c2w_to_opencv_w2c

(c2w: np.ndarray)

src/scripts/convert_dl3dv.py:65

↓ 1 callersFunctionoverlay

( base: Float[Tensor, "channel base_height base_width"], overlay: Float[Tensor, "channel overlay_heigh

src/visualization/layout.py:76

↓ 1 callersFunctionpad

(images: list[Shaped[Tensor, "..."]])

src/visualization/validation_in_3d.py:12

↓ 1 callersFunctionpair

src/model/encoder/heads/dpt_block.py:17

↓ 1 callersMethodpatchify

imgs: (B, 3, H, W) x: (B, L, patch_size**2 *3)

src/model/encoder/backbone/croco/croco.py:203

↓ 1 callersFunctionpivot_parameters_to_extrinsics

( parameters: Float[Tensor, "*#batch 5"], pivot_coordinate_frame: Float[Tensor, "*#batch 3 3"], pi

src/visualization/camera_trajectory/interpolation.py:136

↓ 1 callersFunctionplot_sh

(sh_coefficients, path: Path)

src/misc/sh_rotation.py:77

↓ 1 callersMethodprint_preview_metrics

(self, metrics: dict[str, float | Tensor], methods: list[str] | None = None, overlap_tag: str | None = None)

src/model/model_wrapper.py:629

↓ 1 callersMethodprint_preview_metrics

(self, metrics: dict[str, float], overlap_tag: str | None = None)

src/evaluation/metric_computer.py:116

↓ 1 callersMethodprint_preview_metrics

(self, metrics: dict[str, float], overlap_tag: str | None = None)

src/evaluation/pose_evaluator.py:195

↓ 1 callersFunctionquaternion_to_matrix

( quaternions: Float[Tensor, "*batch 4"], eps: float = 1e-8, )

src/model/encoder/common/gaussians.py:8

↓ 1 callersFunctionreduce_straight_alpha

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

src/visualization/drawing/rendering.py:59

↓ 1 callersFunctionreflect_extrinsics

( extrinsics: Float[Tensor, "*batch 4 4"], )

src/dataset/shims/augmentation_shim.py:8

↓ 1 callersFunctionreg_dense_conf

extract confidence from prediction head output

src/model/encoder/heads/postprocess.py:66

↓ 1 callersFunctionreg_dense_depth

extract 3D points from prediction head output

src/model/encoder/heads/postprocess.py:22

↓ 1 callersFunctionrender

( shape: tuple[int, int], color_function: ColorFunction, device: torch.device, subdivision: in

src/visualization/drawing/rendering.py:118

↓ 1 callersFunctionrender_cameras

(batch: dict, resolution: int)

src/visualization/validation_in_3d.py:93

↓ 1 callersFunctionrender_cuda

( extrinsics: Float[Tensor, "batch 4 4"], intrinsics: Float[Tensor, "batch 3 3"], near: Float[Tens

src/model/decoder/cuda_splatting.py:46

↓ 1 callersFunctionrender_cuda_orthographic

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

src/model/decoder/cuda_splatting.py:136

↓ 1 callersFunctionrender_projections

( gaussians: Gaussians, resolution: int, margin: float = 0.1, draw_label: bool = True, ext

src/visualization/validation_in_3d.py:25

↓ 1 callersMethodrender_video_interpolation

(self, batch: BatchedExample)

src/model/model_wrapper.py:503

↓ 1 callersMethodrender_video_interpolation_exaggerated

(self, batch: BatchedExample)

src/model/model_wrapper.py:530

↓ 1 callersMethodrender_video_wobble

(self, batch: BatchedExample)

src/model/model_wrapper.py:478

↓ 1 callersFunctionresample_patch_embed

Resample the weights of the patch embedding kernel to target resolution. We resample the patch embedding kernel by approximately inverting the eff

src/misc/weight_modify.py:13

↓ 1 callersFunctionrescale

( image: Float[Tensor, "3 h_in w_in"], shape: tuple[int, int], )

src/dataset/shims/crop_shim.py:11

↓ 1 callersFunctionrescale_and_crop

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

src/dataset/shims/crop_shim.py:51

↓ 1 callersFunctionresize

(x_np, _new_size)

src/misc/weight_modify.py:58

↓ 1 callersFunctionrope_2d_cpu

src/model/encoder/backbone/croco/curope/curope.cpp:11

↓ 1 callersMethodrotate_half

src/model/encoder/backbone/croco/pos_embed.py:132

↓ 1 callersFunctionrotate_sh

( sh_coefficients: Float[Tensor, "*#batch n"], rotations: Float[Tensor, "*#batch 3 3"], )

src/misc/sh_rotation.py:10

↓ 1 callersFunctionrsh_cart_2

Computes all real spherical harmonics up to degree 2. This is an autogenerated method. See https://github.com/cheind/torch-spherical-harmonic

src/misc/sht.py:67

↓ 1 callersFunctionrsh_cart_4

Computes all real spherical harmonics up to degree 4. This is an autogenerated method. See https://github.com/cheind/torch-spherical-harmonic

src/misc/sht.py:160

↓ 1 callersFunctionrsh_cart_8

Computes all real spherical harmonics up to degree 8. This is an autogenerated method. See https://github.com/cheind/torch-spherical-harmonic

src/misc/sht.py:833

↓ 1 callersFunctionrun_msaa_pass

( xy: Float[Tensor, "batch height width 2"], color_function: ColorFunction, scale: float, subd

src/visualization/drawing/rendering.py:76

↓ 1 callersMethodsample

( self, scene: str, extrinsics: Float[Tensor, "view 4 4"], intrinsics: Float[T

src/dataset/view_sampler/view_sampler.py:36

↓ 1 callersFunctionsave_video

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

src/misc/image_io.py:77

↓ 1 callersMethodset_center_head

(self, output_mode, head_type, landscape_only, depth_mode, conf_mode)

src/model/encoder/encoder_noposplat.py:86

↓ 1 callersMethodset_downstream_head

(self, output_mode, head_type, landscape_only, depth_mode, conf_mode, patch_size, img_size,

src/model/distiller/dust3d_backbone.py:69

↓ 1 callersMethodset_freeze

src/model/distiller/dust3d_backbone.py:56

↓ 1 callersMethodset_gs_params_head

(self, cfg, head_type)

src/model/encoder/encoder_noposplat.py:97

↓ 1 callersMethodset_gs_params_head

(self, cfg, head_type)

src/model/encoder/encoder_noposplat_multi.py:81

↓ 1 callersMethodset_mean_head

(self, output_mode, head_type, landscape_only, depth_mode, conf_mode)

src/model/encoder/encoder_noposplat_multi.py:68

↓ 1 callersMethodset_step

(self, step: int)

src/misc/step_tracker.py:17

↓ 1 callersMethodsummarize

src/misc/benchmarker.py:35

↓ 1 callersMethodtest_step_align

(self, batch, gaussians)

src/model/model_wrapper.py:285

↓ 1 callersFunctiontrain

(cfg_dict: DictConfig)

↓ 1 callersFunctiontransform_cam2world

Transform points from 3D camera coordinates to 3D world coordinates.

src/geometry/projection.py:31

↓ 1 callersFunctiontransform_world2cam

Transform points from 3D world coordinates to 3D camera coordinates.

src/geometry/projection.py:39

↓ 1 callersFunctionupdate_checkpoint_path

(path: str | None, wandb_cfg: dict)

src/misc/wandb_tools.py:42

↓ 1 callersMethodvisualize

( self, context: dict, global_step: int, )

src/model/encoder/visualization/encoder_visualizer.py:20

↓ 1 callersMethodvisualize_depth

( self, context: BatchedViews, multi_depth: Float[Tensor, "batch view height width sur

src/model/encoder/visualization/encoder_visualizer_epipolar.py:202

↓ 1 callersMethodvisualize_epipolar_color_samples

( self, context_images: Float[Tensor, "batch view 3 height width"], context: BatchedVi

src/model/encoder/visualization/encoder_visualizer_epipolar.py:464

↓ 1 callersMethodvisualize_epipolar_samples

( self, context_images: Float[Tensor, "batch view 3 height width"], sampling: Epipolar

src/model/encoder/visualization/encoder_visualizer_epipolar.py:373

↓ 1 callersMethodvisualize_gaussians

( self, context_images: Float[Tensor, "batch view 3 height width"], opacities: Float[T

src/model/encoder/visualization/encoder_visualizer_epipolar.py:268

↓ 1 callersMethodvisualize_overlaps

( self, context_images: Float[Tensor, "batch view 3 height width"], sampling: Epipolar

src/model/encoder/visualization/encoder_visualizer_epipolar.py:229

↓ 1 callersMethodwith_reduction

src/loss/loss_point.py:135

↓ 1 callersFunctionxy_grid

Output a (H,W,2) array of int32 with output[j,i,0] = i + origin[0] output[j,i,1] = j + origin[1]

src/geometry/ptc_geometry.py:16

FunctionPYBIND11_MODULE

src/model/encoder/backbone/croco/curope/curope.cpp:67

src/loss/loss_point.py:91

( self, t: Float[Tensor, " t"], )

src/visualization/video_render.py:21

( self, xy: Float[Tensor, "*batch 2"], )

src/visualization/drawing/coordinate_conversion.py:12

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

src/visualization/drawing/rendering.py:11

( self, t: Float[Tensor, " t"], )

src/model/model_wrapper.py:78

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

(self, b, h, w, device)

src/model/encoder/backbone/croco/blocks.py:201

← previous next →201–300 of 553, ranked by callers