Closed monajalal closed 9 months ago
duplicate of https://github.com/NVlabs/BundleSDF/issues/111
@wenbowen123 this is not a duplicate. For me, it does happen in the first step. Also, my masks have no problem. Could you please open the issue? I will close it once it gets fixed.
@monajalal have you tried the latest commit as mentioned in https://github.com/NVlabs/BundleSDF/issues/111 ?
yes it worked (I didn't get the error in second step though and got it in first step)
[bundlesdf.py] frame_pairs: 1
[loftr_wrapper.py] image0: torch.Size([1, 1, 400, 400])
[loftr_wrapper.py] net forward
[loftr_wrapper.py] mconf, 0.2004760205745697 0.9993301630020142
[loftr_wrapper.py] pair_ids (1373,)
[loftr_wrapper.py] corres: (1373, 5)
[2023-11-21 11:19:00.265] [warning] [FeatureManager.cpp:1589] start multi pair ransac GPU, pairs#=1
[2023-11-21 11:19:00.266] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074151.917228 #inliers=687, #prev 1187
[bundlesdf.py] frame 1700074151.983942 pose update before
[[ 0.11 -0.988 0.107 0.136]
[-0.774 -0.152 -0.615 0.931]
[ 0.624 -0.015 -0.781 0.868]
[ 0. 0. 0. 1. ]]
[2023-11-21 11:19:00.268] [warning] [FeatureManager.cpp:1095] procrustesByCorrespondence err per point between 1700074151.983942 and 1700074151.917228: 0.000204096
[bundlesdf.py] frame 1700074151.983942 pose update after
[[ 0.096 -0.995 0.022 0.237]
[-0.757 -0.087 -0.647 0.954]
[ 0.646 0.046 -0.762 0.836]
[ 0. 0. 0. 1. ]]
[2023-11-21 11:19:00.269] [warning] [Bundler.cpp:67] forgetting frame 1700074150.182662
[2023-11-21 11:19:00.269] [warning] [FeatureManager.cpp:469] forgetting frame 1700074150.182662
[bundlesdf.py] exceed window size, forget frame 1700074150.182662
[2023-11-21 11:19:00.272] [warning] [Bundler.cpp:435] total keyframes=187, want to select 10
[2023-11-21 11:19:00.300] [warning] [Bundler.cpp:516] ids#=187, max_BA_frames-frames.size()=9
[2023-11-21 11:19:00.300] [warning] [Bundler.cpp:525] frames#=10
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:793] frame 1700074150.115947 and 1700074149.849090 visible=0.811631
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:802] add frame (1700074150.115947, 1700074149.849090) into pairs
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:793] frame 1700074150.449519 and 1700074149.849090 visible=0.923981
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:802] add frame (1700074150.449519, 1700074149.849090) into pairs
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074149.849090 visible=0.914919
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074149.849090) into pairs
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:793] frame 1700074150.115947 and 1700074149.915804 visible=0.838338
[2023-11-21 11:19:00.301] [warning] [Bundler.cpp:802] add frame (1700074150.115947, 1700074149.915804) into pairs
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:793] frame 1700074150.449519 and 1700074149.915804 visible=0.905004
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:802] add frame (1700074150.449519, 1700074149.915804) into pairs
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074149.915804 visible=0.932489
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074149.915804) into pairs
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:793] frame 1700074150.115947 and 1700074149.982519 visible=0.8317
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:802] add frame (1700074150.115947, 1700074149.982519) into pairs
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:793] frame 1700074150.449519 and 1700074149.982519 visible=0.846832
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:802] add frame (1700074150.449519, 1700074149.982519) into pairs
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074149.982519 visible=0.949846
[2023-11-21 11:19:00.302] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074149.982519) into pairs
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:793] frame 1700074150.249376 and 1700074150.115947 visible=0.775355
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:802] add frame (1700074150.249376, 1700074150.115947) into pairs
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:793] frame 1700074150.449519 and 1700074150.115947 visible=0.737151
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:802] add frame (1700074150.449519, 1700074150.115947) into pairs
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:793] frame 1700074151.316803 and 1700074150.115947 visible=0.875138
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:802] add frame (1700074151.316803, 1700074150.115947) into pairs
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:793] frame 1700074151.516945 and 1700074150.115947 visible=0.881712
[2023-11-21 11:19:00.303] [warning] [Bundler.cpp:802] add frame (1700074151.516945, 1700074150.115947) into pairs
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:793] frame 1700074151.650373 and 1700074150.115947 visible=0.859779
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:802] add frame (1700074151.650373, 1700074150.115947) into pairs
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074150.115947 visible=0.935683
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074150.115947) into pairs
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:793] frame 1700074150.449519 and 1700074150.249376 visible=0.767536
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:802] add frame (1700074150.449519, 1700074150.249376) into pairs
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074150.249376 visible=0.946971
[2023-11-21 11:19:00.304] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074150.249376) into pairs
[2023-11-21 11:19:00.305] [warning] [Bundler.cpp:793] frame 1700074151.316803 and 1700074150.449519 visible=0.90125
[2023-11-21 11:19:00.305] [warning] [Bundler.cpp:802] add frame (1700074151.316803, 1700074150.449519) into pairs
[2023-11-21 11:19:00.305] [warning] [Bundler.cpp:793] frame 1700074151.516945 and 1700074150.449519 visible=0.907337
[2023-11-21 11:19:00.305] [warning] [Bundler.cpp:802] add frame (1700074151.516945, 1700074150.449519) into pairs
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:793] frame 1700074151.650373 and 1700074150.449519 visible=0.905742
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:802] add frame (1700074151.650373, 1700074150.449519) into pairs
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074150.449519 visible=0.889362
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074150.449519) into pairs
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074151.316803 visible=0.888084
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074151.316803) into pairs
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074151.516945 visible=0.891172
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074151.516945) into pairs
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:793] frame 1700074151.983942 and 1700074151.650373 visible=0.890534
[2023-11-21 11:19:00.306] [warning] [Bundler.cpp:802] add frame (1700074151.983942, 1700074151.650373) into pairs
[bundlesdf.py] frame_pairs: 24
[2023-11-21 11:19:00.306] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.115947, 1700074149.849090)
[2023-11-21 11:19:00.307] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.449519, 1700074149.849090)
[2023-11-21 11:19:00.308] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.115947, 1700074149.915804)
[2023-11-21 11:19:00.308] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.449519, 1700074149.915804)
[2023-11-21 11:19:00.309] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.115947, 1700074149.982519)
[2023-11-21 11:19:00.309] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.449519, 1700074149.982519)
[2023-11-21 11:19:00.311] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.249376, 1700074150.115947)
[2023-11-21 11:19:00.311] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.449519, 1700074150.115947)
[2023-11-21 11:19:00.311] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074151.316803, 1700074150.115947)
[2023-11-21 11:19:00.311] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074151.516945, 1700074150.115947)
[2023-11-21 11:19:00.311] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074151.650373, 1700074150.115947)
[2023-11-21 11:19:00.312] [warning] [FeatureManager.cpp:2690] _raw_matches found exsting pair (1700074150.449519, 1700074150.249376)
[loftr_wrapper.py] image0: torch.Size([12, 1, 400, 400])
[loftr_wrapper.py] net forward
[loftr_wrapper.py] mconf, 0.20008717477321625 0.9882730841636658
[loftr_wrapper.py] pair_ids (2947,)
[loftr_wrapper.py] corres: (2947, 5)
[2023-11-21 11:19:00.457] [warning] [FeatureManager.cpp:1589] start multi pair ransac GPU, pairs#=12
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1695] after ransac, frame 1700074151.983942 and 1700074149.849090 has too few matches #0, ignore
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1695] after ransac, frame 1700074151.983942 and 1700074149.915804 has too few matches #0, ignore
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1695] after ransac, frame 1700074151.983942 and 1700074149.982519 has too few matches #3, ignore
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074150.115947 #inliers=7, #prev 153
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074150.249376 #inliers=19, #prev 197
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1695] after ransac, frame 1700074151.316803 and 1700074150.449519 has too few matches #2, ignore
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1695] after ransac, frame 1700074151.516945 and 1700074150.449519 has too few matches #3, ignore
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1695] after ransac, frame 1700074151.650373 and 1700074150.449519 has too few matches #4, ignore
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074150.449519 #inliers=6, #prev 179
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074151.316803 #inliers=86, #prev 280
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074151.516945 #inliers=11, #prev 194
[2023-11-21 11:19:00.484] [warning] [FeatureManager.cpp:1699] ransac makes match betwee frame 1700074151.983942 1700074151.650373 #inliers=77, #prev 363
#optimizeGPU frames=10, #keyframes=187, #_frames=193
1700074149.849090 1700074149.915804 1700074149.982519 1700074150.115947 1700074150.249376 1700074150.449519 1700074151.316803 1700074151.516945 1700074151.650373 1700074151.983942
[2023-11-21 11:19:00.486] [warning] [Bundler.cpp:920] OptimizerGPU begin, global_corres#=206
global_corres=206
maxNumResiduals / maxNumberOfImages = 216206 / 10 = 21620
m_maxNumberOfImages*m_maxCorrPerImage = 10 x 206 = 2060
m_solver->solve Time difference = 4.021[ms]
[2023-11-21 11:19:00.496] [warning] [Bundler.cpp:924] OptimizerGPU finish
[2023-11-21 11:19:00.496] [warning] [Bundler.cpp:302] frame 1700074151.983942 not selected as keyframe since its rot diff with frame 1700074151.516945 is 3.48706 deg
[bundlesdf.py] processNewFrame done 1700074151.983942
[bundlesdf.py] rematch_after_nerf: True
[2023-11-21 11:19:00.497] [warning] [Bundler.cpp:961] Welcome saveNewframeResult
[2023-11-21 11:19:00.532] [warning] [Bundler.cpp:1110] saveNewframeResult done
[2023-11-21 11:19:04.973] [warning] [Bundler.cpp:49] Connected to nerf_port 9999
[2023-11-21 11:19:04.973] [warning] [FeatureManager.cpp:2084] Connected to port 5555
default_cfg {'backbone_type': 'ResNetFPN', 'resolution': (8, 2), 'fine_window_size': 5, 'fine_concat_coarse_feat': True, 'resnetfpn': {'initial_dim': 128, 'block_dims': [128, 196, 256]}, 'coarse': {'d_model': 256, 'd_ffn': 256, 'nhead': 8, 'layer_names': ['self', 'cross', 'self', 'cross', 'self', 'cross', 'self', 'cross'], 'attention': 'linear', 'temp_bug_fix': False}, 'match_coarse': {'thr': 0.2, 'border_rm': 2, 'match_type': 'dual_softmax', 'dsmax_temperature': 0.1, 'skh_iters': 3, 'skh_init_bin_score': 1.0, 'skh_prefilter': True, 'train_coarse_percent': 0.4, 'train_pad_num_gt_min': 200}, 'fine': {'d_model': 128, 'd_ffn': 128, 'nhead': 8, 'layer_names': ['self', 'cross'], 'attention': 'linear'}}
[bundlesdf.py] last_stamp 1700074151.983942
[bundlesdf.py] keyframes#: 187
[tool.py] compute_scene_bounds_worker start
[tool.py] compute_scene_bounds_worker done
[tool.py] merge pcd
[tool.py] compute_translation_scales done
translation_cvcam=[-0.00473613 -0.00114112 0.01014452], sc_factor=2.0600853021701306
[nerf_runner.py] Octree voxel dilate_radius:1
level 0, resolution: 16
level 1, resolution: 20
level 2, resolution: 24
level 3, resolution: 28
level 4, resolution: 34
level 5, resolution: 41
level 6, resolution: 49
level 7, resolution: 59
level 8, resolution: 71
level 9, resolution: 85
level 10, resolution: 102
level 11, resolution: 123
level 12, resolution: 148
level 13, resolution: 177
level 14, resolution: 213
level 15, resolution: 256
GridEncoder: input_dim=3 n_levels=16 level_dim=2 resolution=16 -> 256 per_level_scale=1.2030 params=(20411696, 2) gridtype=hash align_corners=False
sc_factor 2.0600853021701306
translation [-0.00473613 -0.00114112 0.01014452]
[nerf_runner.py] denoise cloud
[nerf_runner.py] Denoising rays based on octree cloud
[nerf_runner.py] bad_mask#=47409
rays torch.Size([8815005, 12])
Start training
[nerf_runner.py] train progress 0/2001
[nerf_runner.py] Iter: 0, valid_samples: 654784/655360, valid_rays: 2047/2048, loss: 19.2875576, rgb_loss: 18.9341164, rgb0_loss: 0.0000000, fs_rgb_loss: 0.0000000, depth_loss: 0.0000000, depth_loss0: 0.0000000, fs_loss: 0.0718253, point_cloud_loss: 0.0000000, point_cloud_normal_loss: 0.0000000, sdf_loss: 0.1769290, eikonal_loss: 0.0000000, variation_loss: 0.0000000, truncation(meter): 0.0100000, pose_reg: 0.0000000, reg_features: 0.1046863,
[nerf_runner.py] train progress 200/2001
[nerf_runner.py] train progress 400/2001
[nerf_runner.py] train progress 600/2001
[nerf_runner.py] train progress 800/2001
[nerf_runner.py] train progress 1000/2001
[nerf_runner.py] train progress 1200/2001
[nerf_runner.py] train progress 1400/2001
[nerf_runner.py] train progress 1600/2001
[nerf_runner.py] train progress 1800/2001
[nerf_runner.py] train progress 2000/2001
cp: cannot stat '/home/mona/BundleSDF/pallet/out//nerf_with_bundletrack_online/image_step_*.png': No such file or directory
[nerf_runner.py] query_pts:torch.Size([114084125, 3]), valid:45562520
[nerf_runner.py] Running Marching Cubes
[nerf_runner.py] done V:(86787, 3), F:(171710, 3)
[acceleratesupport.py] OpenGL_accelerate module loaded
[arraydatatype.py] Using accelerated ArrayDatatype
project train_images 0/187
project train_images 1/187
project train_images 2/187
project train_images 3/187
project train_images 4/187
project train_images 5/187
project train_images 6/187
/home/mona/BundleSDF/nerf_runner.py:1532: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
uvs_unique = torch.stack((uvs_flat_unique%(W-1), uvs_flat_unique//(W-1)), dim=-1).reshape(-1,2)
project train_images 7/187
project train_images 8/187
project train_images 9/187
project train_images 10/187
project train_images 11/187
project train_images 12/187
project train_images 13/187
project train_images 14/187
project train_images 15/187
project train_images 16/187
project train_images 17/187
project train_images 18/187
project train_images 19/187
project train_images 20/187
project train_images 21/187
project train_images 22/187
project train_images 23/187
project train_images 24/187
project train_images 25/187
project train_images 26/187
project train_images 27/187
project train_images 28/187
project train_images 29/187
project train_images 30/187
project train_images 31/187
project train_images 32/187
project train_images 33/187
project train_images 34/187
project train_images 35/187
project train_images 36/187
project train_images 37/187
project train_images 38/187
project train_images 39/187
project train_images 40/187
project train_images 41/187
project train_images 42/187
project train_images 43/187
project train_images 44/187
project train_images 45/187
project train_images 46/187
project train_images 47/187
project train_images 48/187
project train_images 49/187
project train_images 50/187
project train_images 51/187
project train_images 52/187
project train_images 53/187
project train_images 54/187
project train_images 55/187
project train_images 56/187
project train_images 57/187
project train_images 58/187
project train_images 59/187
project train_images 60/187
project train_images 61/187
project train_images 62/187
project train_images 63/187
project train_images 64/187
project train_images 65/187
project train_images 66/187
project train_images 67/187
project train_images 68/187
project train_images 69/187
project train_images 70/187
project train_images 71/187
project train_images 72/187
project train_images 73/187
project train_images 74/187
project train_images 75/187
project train_images 76/187
project train_images 77/187
project train_images 78/187
project train_images 79/187
project train_images 80/187
project train_images 81/187
project train_images 82/187
project train_images 83/187
project train_images 84/187
project train_images 85/187
project train_images 86/187
project train_images 87/187
project train_images 88/187
project train_images 89/187
project train_images 90/187
project train_images 91/187
project train_images 92/187
project train_images 93/187
project train_images 94/187
project train_images 95/187
project train_images 96/187
project train_images 97/187
project train_images 98/187
project train_images 99/187
project train_images 100/187
project train_images 101/187
project train_images 102/187
project train_images 103/187
project train_images 104/187
project train_images 105/187
project train_images 106/187
project train_images 107/187
project train_images 108/187
project train_images 109/187
project train_images 110/187
project train_images 111/187
project train_images 112/187
project train_images 113/187
project train_images 114/187
project train_images 115/187
project train_images 116/187
project train_images 117/187
project train_images 118/187
project train_images 119/187
project train_images 120/187
project train_images 121/187
project train_images 122/187
project train_images 123/187
project train_images 124/187
project train_images 125/187
project train_images 126/187
project train_images 127/187
project train_images 128/187
project train_images 129/187
project train_images 130/187
project train_images 131/187
project train_images 132/187
project train_images 133/187
project train_images 134/187
project train_images 135/187
project train_images 136/187
project train_images 137/187
project train_images 138/187
project train_images 139/187
project train_images 140/187
project train_images 141/187
project train_images 142/187
project train_images 143/187
project train_images 144/187
project train_images 145/187
project train_images 146/187
project train_images 147/187
project train_images 148/187
project train_images 149/187
project train_images 150/187
project train_images 151/187
project train_images 152/187
project train_images 153/187
project train_images 154/187
project train_images 155/187
project train_images 156/187
project train_images 157/187
project train_images 158/187
project train_images 159/187
project train_images 160/187
project train_images 161/187
project train_images 162/187
project train_images 163/187
project train_images 164/187
project train_images 165/187
project train_images 166/187
project train_images 167/187
project train_images 168/187
project train_images 169/187
project train_images 170/187
project train_images 171/187
project train_images 172/187
project train_images 173/187
project train_images 174/187
project train_images 175/187
project train_images 176/187
project train_images 177/187
project train_images 178/187
project train_images 179/187
project train_images 180/187
project train_images 181/187
project train_images 182/187
project train_images 183/187
project train_images 184/187
project train_images 185/187
project train_images 186/187
/home/mona/BundleSDF/nerf_runner.py:1539: RuntimeWarning: invalid value encountered in cast
tex_image = np.clip(tex_image,0,255).astype(np.uint8)
Done
[2023-11-21 11:21:03.507] [warning] [Bundler.cpp:59] Destructor
[2023-11-21 11:21:03.909] [warning] [Bundler.cpp:59] Destructor
my created mesh looks very weird though (my object looks like a rectangular cuboid itself)
For now, I close this issue since the main problem is resolved.
Could you please tell what is the order you have used for your cam_K.txt
file? Thank you so much for the new push to code.
@wenbowen123 I think I got it figured https://github.com/IntelRealSense/realsense-ros/issues/2935#issuecomment-1821642149
Hello, I encountered the same problem, how did you solve it(ValueError: need at least one array to concatenate)?
@Wahaha-code you need depth-aligned depth and rgb capture. I used ros realsense for this purpose in a ros noetic docker. My camera is D435.
Thank you for your guidance. In fact, I have always had a problem. During my reconstruction process, which is the first step, due to the small number of matching points between the two frames, it will often be interrupted. I have to press the c key frequently to continue running. . I want to know how I can better collect my data. At the same time, I found that when using xmem to split image files, frames often skip. Is this the cause of this problem? I don't know how to solve this problem.
I get an error in this step. How should I fix this?
I am following ros realsense depth aligned capture and use xmem for segmentation.
Here is one of the depth images:
here is the mesh_cleaned.obj that is created that doesn't resemble an espresso cup.