# tag=r-robotplant-1 start=2026-11-03T18:24:47+01:00 cmd=<home>/supratex-0311/venv/bin/python scripts/run_example.py --config <home>/supratex-0311/ready/models.json --input <home>/supratex-0311/in-rgb/robot-plant.png --output <home>/supratex-0311/out/r-robotplant-1.glb
[    0.62] [Supra-Tex inference] attention=sdpa; sparse_attention=sdpa; low_vram=False
[    0.62] [1/2] Foreground, MoGe-2, geometry, material maps -> <home>/supratex-0311/out/r-robotplant-1_work/input
[    0.62] [Supra-Tex inference] attention=sdpa; sparse_attention=sdpa; low_vram=False
[   39.32] [2/2] Surface observations, PBR completion, GLB export -> <home>/supratex-0311/out/r-robotplant-1.glb
[   39.32] [Supra-Tex inference] attention=sdpa; sparse_attention=sdpa; low_vram=False
[   39.54] [SPARSE] Conv backend: flex_gemm; Attention backend: sdpa; Batch broadcast: direct
[   39.54] Floaters: removed 0 of 57 components (0 of 9698656 faces)
[   49.68] Observation: silhouette IoU 0.951 (geometry inside image 0.976, image covered 0.974); admitted 238439 of 247323 trusted pixels (missed geometry 341, depth edge 3594, image-depth mismatch 4949)
[   49.68] Image depth gate: applied; 280850 paired depth pixels, 9498 mismatch pixels
[   49.68] Observation image depth: excluded 1131 additional voxel samples crossing the mismatch mask; 184694 observed voxels
[   50.69] [ATTENTION] Using backend: sdpa
[   50.69] Observation cache: enabled
[   62.15] 
Extracting GLB:   0%|          | 0/6 [00:00<?, ?it/s]
Building BVH:  17%|█▋        | 1/6 [00:00<00:00, 87.87it/s]
Building BVH:  33%|███▎      | 2/6 [00:02<00:05,  1.35s/it]
Cleaning mesh:  33%|███▎      | 2/6 [00:02<00:05,  1.35s/it]<home>/supratex-0311/venv/lib/python3.12/site-packages/cumesh/remeshing.py:220: UserWarning: Using torch.cross without specifying the dim arg is deprecated.
[   62.15] Please either pass the dim explicitly or simply use torch.linalg.cross.
[   62.15] The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at /__w/pytorch/pytorch/aten/src/ATen/native/Cross.cpp:63.)
[   62.15]   normals0 = torch.cross(mesh_vertices[atempt_triangles_0[:, 1]] - mesh_vertices[atempt_triangles_0[:, 0]], mesh_vertices[atempt_triangles_0[:, 2]] - mesh_vertices[atempt_triangles_0[:, 0]])
[   81.77] 
Cleaning mesh:  50%|█████     | 3/6 [00:03<00:02,  1.06it/s]
Parameterizing new mesh:  50%|█████     | 3/6 [00:03<00:02,  1.06it/s]
Parameterizing new mesh:  67%|██████▋   | 4/6 [00:15<00:10,  5.09s/it]
Sampling attributes:  67%|██████▋   | 4/6 [00:15<00:10,  5.09s/it]    
Sampling attributes:  83%|████████▎ | 5/6 [00:16<00:03,  3.90s/it]
Finalizing mesh:  83%|████████▎ | 5/6 [00:16<00:03,  3.90s/it]    
Finalizing mesh: 100%|██████████| 6/6 [00:22<00:00,  4.47s/it]
Finalizing mesh: 100%|██████████| 6/6 [00:22<00:00,  3.73s/it]
[   86.92] Textured mesh: <home>/supratex-0311/out/r-robotplant-1.glb
[   86.92] Intermediate files and run receipt: <home>/supratex-0311/out/r-robotplant-1_work