MCPcopy Create free account

hub / github.com/GasaiYU/PartRM / functions

Functions389 in github.com/GasaiYU/PartRM

↓ 10 callersMethod__init__
(self, config: ViTConfig)
preprocess/src/models/encoder/dino.py:308
↓ 6 callersMethod__init__
( self, in_channels: int = 3, out_channels: int = 3, down_channels: Tuple[int,
core/unet.py:237
↓ 5 callersMethod__init__
(self, state_dict: Dict[str, torch.Tensor])
preprocess/zero123plus/pipeline.py:230
↓ 5 callersFunctionget_rays
(pose, h, w, fovy, opengl=True)
core/utils.py:10
↓ 4 callersFunctionFOV_to_intrinsics
Creates a 3x3 camera intrinsics matrix from the camera field of view, specified in degrees. Note the intrinsics are returned as normalized by
preprocess/src/utils/camera_util.py:84
↓ 4 callersFunctionextract_into_tensor
(a, t, x_shape)
preprocess/zero123plus/model.py:38
↓ 4 callersFunctioninstantiate_from_config
(config)
preprocess/src/utils/train_util.py:11
↓ 4 callersMethodload_im
replace background pixel with random color in rendering
preprocess/src/data/objaverse.py:110
↓ 4 callersMethodprepare
(self)
preprocess/zero123plus/pipeline.py:314
↓ 4 callersFunctionsave_combined_obj_with_texture
(verts, normals, textures, faces, faces_vt, faces_vn, mtl_files, mtl_dict, output_obj)
PartDrag4D/preprocess/process_data_textured_uv.py:209
↓ 4 callersFunctionscene_root_objects
()
PartDrag4D/rendering/blender_script.py:281
↓ 3 callersFunctioncenter_looking_at_camera_pose
Create OpenGL camera extrinsics from camera locations and look-at position. camera_position: (M, 3) or (3,) look_at: (3) up_world: (
preprocess/src/utils/camera_util.py:16
↓ 3 callersFunctiondeform_part
(idx, key, origin_verts, pts, deform_num)
PartDrag4D/preprocess/animate_data.py:118
↓ 3 callersMethodget_texture_prediction
Predict Texture given triplanes :param planes: the triplane feature map :param tex_pos: Position we want to query the texture
preprocess/src/models/lrm_mesh.py:192
↓ 3 callersFunctionprocess_image
(image_path)
compute_metrics.py:49
↓ 3 callersFunctionsample_from_planes
(plane_axes, plane_features, coordinates, mode='bilinear', padding_mode='zeros', box_warp=None)
preprocess/src/models/renderer/utils/renderer.py:62
↓ 3 callersFunctionscene_bbox
Calculate the bounding box of a single object or the entire scene.
PartDrag4D/rendering/blender_script.py:100
↓ 3 callersFunctionsort_edges
(edges_ex2)
preprocess/src/models/geometry/rep_3d/dmtet.py:47
↓ 3 callersMethodtranspose_for_scores
(self, x: torch.Tensor)
preprocess/src/models/encoder/dino.py:172
↓ 2 callersMethod__init__
(self, num_freqs=64, temperature=100)
core/drag_embedding.py:7
↓ 2 callersMethod_forward_pass
Additional filtering is applied to filter out-of-box samples. Modifications made by Zexin He.
preprocess/src/models/renderer/utils/renderer.py:121
↓ 2 callersMethod_linear_interp
Computes the location of zero-crossings on 'edges_x' using linear interpolation with 'edges_weight'.
preprocess/src/models/geometry/rep_3d/flexicubes.py:331
↓ 2 callersMethodactivation_factory
(options: dict)
preprocess/src/models/renderer/utils/renderer.py:114
↓ 2 callersMethodencode_condition_image
(self, image: torch.Tensor)
preprocess/zero123plus/pipeline.py:324
↓ 2 callersFunctionfind_indices
(tensor, numbers_list)
PartDrag4D/preprocess/animate_data.py:110
↓ 2 callersMethodforward
(self, x: Tensor)
core/attention.py:51
↓ 2 callersMethodforward
(self, lrm_generator_input)
preprocess/src/model_mesh.py:185
↓ 2 callersMethodforward
(self, lrm_generator_input)
preprocess/src/model.py:169
↓ 2 callersMethodforward_geometry
Main function of our Generator. It first generate 3D mesh, then render it into 2D image with given `render_cameras`. :param p
preprocess/src/models/lrm_mesh.py:270
↓ 2 callersMethodforward_points
(self, planes, points: torch.Tensor, chunk_size: int = 2**20)
preprocess/src/models/renderer/synthesizer.py:178
↓ 2 callersFunctiongen_rgba
Generate rgba images from rgb images which are with white background. Args: image_path (str): Path to the rgb image.
preprocess/gen_rgba.py:7
↓ 2 callersFunctiongenerate_planes
Defines planes by the three vectors that form the "axes" of the plane. Should work with arbitrary number of planes and planes of arbitrar
preprocess/src/models/renderer/utils/renderer.py:28
↓ 2 callersMethodget_geometry_prediction
Function to generate mesh with give triplanes :param planes: triplane features
preprocess/src/models/lrm_mesh.py:159
↓ 2 callersMethodget_mesh
(self, v_deformed_nx3, sdf_n, with_uv=False, indices=None)
preprocess/src/models/geometry/rep_3d/dmtet.py:434
↓ 2 callersFunctioninterpolate
(attr, rast, attr_idx, rast_db=None)
preprocess/src/models/geometry/render/neural_render.py:17
↓ 2 callersFunctionload_obj_with_texture
(obj_path)
PartDrag4D/preprocess/process_data_textured_uv.py:85
↓ 2 callersFunctionmodulate
(x, shift, scale)
preprocess/src/models/encoder/dino.py:301
↓ 2 callersMethodprepare_batch_data
(self, batch)
preprocess/zero123plus/model.py:105
↓ 2 callersMethodprocess_state_data
(self, uid, zero123_uid, vids, is_input=False)
core/eval_dataset_partdrag4d.py:90
↓ 2 callersMethodprocess_state_data
(self, image_path0, camera_dir, vids)
core/train_dataset_objaverse_hq.py:184
↓ 2 callersMethodprocess_state_data
(self, uid, vids)
core/train_dataset_partdrag4d.py:89
↓ 2 callersMethodprocess_state_data
(self, image_path0, zero123_uid, camera_dir, vids, is_input=False)
core/eval_dataset_objaverse_hq.py:184
↓ 2 callersMethodproject_drags
(self, drags, cam_view)
core/eval_dataset_partdrag4d.py:182
↓ 2 callersMethodproject_drags
(self, drags, cam_view)
core/train_dataset_partdrag4d.py:177
↓ 2 callersMethodrender
(self, gaussians, cam_view, cam_view_proj, cam_pos, bg_color=None, scale_modifier=1)
core/gs.py:31
↓ 2 callersMethodrun_forward
(self, colors, densities, depths, rendering_options, normals=None)
preprocess/src/models/renderer/utils/ray_marcher.py:30
↓ 2 callersMethodrun_model
(self, planes, decoder, sample_coordinates, sample_directions, options)
preprocess/src/models/renderer/utils/renderer.py:197
↓ 2 callersMethodsample_stratified
Return depths of approximately uniformly spaced samples along rays.
preprocess/src/models/renderer/utils/renderer.py:239
↓ 2 callersFunctionto_rgb_image
(maybe_rgba: Image.Image)
preprocess/zero123plus/pipeline.py:31
↓ 2 callersFunctionunscale_image
(image)
preprocess/zero123plus/model.py:33
↓ 2 callersFunctionxatlas_uvmap
(ctx, mesh_v, mesh_pos_idx, resolution)
preprocess/src/models/geometry/rep_3d/extract_texture_map.py:20
↓ 1 callersFunctionBKE_camera_sensor_fit
(p_sensor_fit, sizex, sizey)
PartDrag4D/rendering/blender_script.py:142
↓ 1 callersFunctionBKE_camera_sensor_size
(p_sensor_fit, sensor_x, sensor_y)
PartDrag4D/rendering/blender_script.py:125
↓ 1 callersMethod__getattr__
(self, name: str)
preprocess/zero123plus/pipeline.py:192
↓ 1 callersMethod__init__
( self, dim: int, num_heads: int = 8, qkv_bias: bool = False, proj_bia
core/attention.py:32
↓ 1 callersMethod__init__
(self, root_dir='objaverse/', meta_fname='valid_paths.json', image_dir='rendering_zero
preprocess/src/data/objaverse_zero123plus.py:61
↓ 1 callersMethod__init__
(self, root_dir='objaverse/', meta_fname='valid_paths.json', input_image_dir='renderin
preprocess/src/data/objaverse.py:75
↓ 1 callersMethod__init__
(self, n_features: int, hidden_dim: int = 64, num_layers: int = 4, activation: nn.Module = nn
preprocess/src/models/renderer/synthesizer_mesh.py:23
↓ 1 callersMethod__init__
(self, n_features: int, hidden_dim: int = 64, num_layers: int = 4, activation: nn.Module = nn
preprocess/src/models/renderer/synthesizer.py:25
↓ 1 callersMethod__init__
(self)
preprocess/src/models/renderer/utils/ray_sampler.py:23
↓ 1 callersMethod__init__
( self, inner_dim: int, image_feat_dim: int, triplane_low_res: int,
preprocess/src/models/decoder/transformer.py:73
↓ 1 callersMethod__len__
(self)
core/eval_dataset_partdrag4d.py:87
↓ 1 callersMethod__len__
(self)
core/train_dataset_partdrag4d.py:86
↓ 1 callersMethod_build_activation_factory
(self)
preprocess/src/models/renderer/utils/renderer.py:113
↓ 1 callersMethod_build_dino
(model_name: str, proxy_error_retries: int = 3, proxy_error_cooldown: int = 5)
preprocess/src/models/encoder/dino_wrapper.py:67
↓ 1 callersMethod_compute_reg_loss
Regularizer L_dev as in Equation 8
preprocess/src/models/geometry/rep_3d/flexicubes.py:218
↓ 1 callersMethod_compute_vd
Computes the location of dual vertices as described in Section 4.2
preprocess/src/models/geometry/rep_3d/flexicubes.py:357
↓ 1 callersMethod_freeze
(self)
preprocess/src/models/encoder/dino_wrapper.py:60
↓ 1 callersMethod_get_case_id
Obtains the ID of topology cases based on cell corner occupancy. This function resolves the ambiguity in the Dual Marching Cubes (DM
preprocess/src/models/geometry/rep_3d/flexicubes.py:252
↓ 1 callersMethod_identify_surf_cubes
Identifies grid cubes that intersect with the underlying surface by checking if the signs at all corners are not identical.
preprocess/src/models/geometry/rep_3d/flexicubes.py:320
↓ 1 callersMethod_identify_surf_edges
Identifies grid edges that intersect with the underlying surface by checking for opposite signs. As each edge can be shared by multi
preprocess/src/models/geometry/rep_3d/flexicubes.py:295
↓ 1 callersMethod_normalize_weights
Normalizes the given weights to be non-negative. If input weights are None, it creates and returns a set of weights of ones.
preprocess/src/models/geometry/rep_3d/flexicubes.py:228
↓ 1 callersMethod_solve_vd_QEF
(self, p_bxnx3, norm_bxnx3, c_bx3=None)
preprocess/src/models/geometry/rep_3d/flexicubes.py:343
↓ 1 callersMethod_tetrahedralize
Tetrahedralizes the interior volume to produce a tetrahedral mesh, as described in Section 4.5.
preprocess/src/models/geometry/rep_3d/flexicubes.py:500
↓ 1 callersMethod_triangulate
Connects four neighboring dual vertices to form a quadrilateral. The quadrilaterals are then split into triangles based on the gamma
preprocess/src/models/geometry/rep_3d/flexicubes.py:449
↓ 1 callersMethodcompute_loss
(self, noise_pred, noise_gt)
preprocess/zero123plus/model.py:233
↓ 1 callersMethodcompute_loss
(self, render_out, render_gt)
preprocess/src/model_mesh.py:243
↓ 1 callersMethodcompute_loss
(self, render_out, render_gt)
preprocess/src/model.py:243
↓ 1 callersFunctioncompute_lpips
(src_images, tgt_images, lpips_loss_fn)
compute_metrics.py:31
↓ 1 callersFunctioncompute_psnr
(src_images, tgt_images)
compute_metrics.py:45
↓ 1 callersFunctioncompute_ssim
(src_images, tgt_images)
compute_metrics.py:19
↓ 1 callersFunctioncompute_vertex_normal
(v_pos, t_pos_idx)
preprocess/src/models/geometry/render/neural_render.py:42
↓ 1 callersMethodconstruct_voxel_grid
Generates a voxel grid based on the specified resolution. Args: res (int or list[int]): The resolution of the voxel grid
preprocess/src/models/geometry/rep_3d/flexicubes.py:100
↓ 1 callersFunctioncreate_mt_variable
(device)
preprocess/src/models/geometry/rep_3d/dmtet.py:20
↓ 1 callersFunctioncreate_tetmesh_variables
(device='cuda')
preprocess/src/models/geometry/rep_3d/dmtet.py:107
↓ 1 callersFunctioncustomized_normalize_scene
()
PartDrag4D/rendering/blender_script.py:322
↓ 1 callersFunctiondot
(x, y)
preprocess/src/models/geometry/render/neural_render.py:38
↓ 1 callersMethodencode_condition_image
(self, images)
preprocess/zero123plus/model.py:137
↓ 1 callersMethodencode_target_images
(self, images)
preprocess/zero123plus/model.py:146
↓ 1 callersMethodforward_cond
(self, noisy_cond_lat, timestep, encoder_hidden_states, class_labels, ref_dict, is_cfg_guidance, **kwargs)
preprocess/zero123plus/pipeline.py:107
↓ 1 callersMethodforward_gaussians
(self, images, drags_start=None, drags_end=None)
core/models.py:98
↓ 1 callersMethodforward_grid
(self, planes, grid_size: int, aabb: torch.Tensor = None)
preprocess/src/models/renderer/synthesizer.py:146
↓ 1 callersMethodforward_lrm_generator
(self, images, cameras, render_cameras, render_size=512)
preprocess/src/model_mesh.py:171
↓ 1 callersMethodforward_lrm_generator
( self, images, cameras, render_cameras, render_size=192,
preprocess/src/model.py:136
↓ 1 callersMethodforward_planes
(self, images, cameras)
preprocess/src/models/lrm.py:68
↓ 1 callersMethodforward_planes
(self, images, cameras)
preprocess/src/models/lrm_mesh.py:88
↓ 1 callersMethodforward_unet
(self, latents, t, prompt_embeds, cond_latents)
preprocess/zero123plus/model.py:155
↓ 1 callersMethodforward_vision_encoder
(self, images)
preprocess/zero123plus/model.py:122
↓ 1 callersFunctiongen_rand_num
(num_range, cur_num)
preprocess/gen_propagate_drags.py:24
↓ 1 callersFunctiongen_rgba_from_filelist
Generate rgba images from rgb images which are with white background. Args: file_list_path (str): Path to the file list.
preprocess/gen_rgba.py:27
next →1–100 of 389, ranked by callers