3 views
Friedrich-M/UniMate
[SIGGRAPH Asia 2026] UniMate: One Unified Model to Animate Diverse Skeletons
Python★ 1,123+217 that day#10 on trending
C69.3/100
Duplication72
4.1% in python, bash, perlDead code98
0.1%Complexity48
54% The score is jscpd's own --health model: markup, data and text left out, tests kept. The numbers below are the trending scan's.
4.06%duplicated code · 1,540 of 37,949 lines
113clones in code
142code files of 159 scanned
5.24%duplicated over all files · 132 clones
Most complex files
- data_process/tools/patch_annotations.py267 cx
- unimate/dataset/mixture/dataset.py267 cx
- data_process/utils/blender_export.py220 cx
- data_process/utils/blender_render.py210 cx
- unimate/inference/sample.py176 cx
- data_process/utils/blender_rig.py161 cx
- data_process/vlm_caption/classify_category.py150 cx
- data_process/joint_annotation/names_clean_rule.py134 cx
- data_process/utils/plotting.py134 cx
- unimate/models/diffusion/gaussian_diffusion.py132 cx
Dead code 0.06% unused · 11 findings
- data_process/utils/blender_export.py:collect_joint_names_from_markersunused-import
- data_process/joint_annotation/names_clean_rule.py:_looks_unmappedunused-symbol
- data_process/tools/patch_annotations.py:fkunused-import
- data_process/tools/patch_annotations.py:qrotunused-import
- data_process/joint_annotation/names_clean_rule.py:_UNMAPPED_PATTERNunused-symbol
- data_process/motion_export/export_truebones.py:bpyunused-import
- data_process/motion_rendering/render_mixamo.py:bpyunused-import
- data_process/motion_rendering/render_objaverse.py:bpyunused-import
- data_process/motion_rendering/render_truebones.py:bpyunused-import
- data_process/utils/vlm.py:flash_attnunused-import
The code number leaves out tests, fixtures, docs, examples, data files, styles, translations and vendored code.
Largest clones in the code
- 33 lines in 2 placespython359 tokens
238new_motion = np.zeros((n_frames, 1, D), dtype=motion.dtype) 239new_motion[:, 0, 3:9] = motion[:, ji, 3:9] 240 241aug['motion'] = np.concatenate( 242 [motion[:, :ji], new_motion, motion[:, ji:]], axis=1, 243) 244aug['offsets'] = np.concatenate( 245 [offsets[:ji], offset_new[None], offsets[ji:]], axis=0, 246) 247aug['offsets'][ji + 1] = offset_ji_remFirst 10 of 33 lines.
- 40 lines in 2 placespython295 tokensdata_process/motion_rendering/render_mixamo.py:102–141data_process/motion_rendering/render_truebones.py:106–145
102 "mesh_animation/animate_mixamo.py.") 103parser.add_argument("--output_dir", type=str, required=True, 104 help="Output directory.") 105parser.add_argument("--scale", type=float, default=1.0, 106 help="Scene normalization scale.") 107parser.add_argument("--camera_dist", type=float, default=1.5, 108 help="Camera distance from origin.") 109parser.add_argument("--resolution", type=int, default=512, 110 help="Render resolution (square).") 111parser.add_argument("--fps", type=int, default=RENDER_FPS,First 10 of 40 lines.
- 33 lines in 2 placespython248 tokens
147(shift_s, scale_s, gate_s, 148 shift_t, scale_t, gate_t, 149 shift_m, scale_m, gate_m) = self.adaLN_modulation(c).chunk(9, dim=-1) 150 151def expand_to_x(z): 152 return z[:, None, None, :] 153 154use_ckpt = self.gradient_checkpointing and self.training 155 156# spatial attnFirst 10 of 33 lines.
7 more
- 8 lines in 3 placespython121 tokens
- 34 lines in 2 placespython240 tokens
- 25 lines in 2 placespython205 tokens
- 15 lines in 5 placespython51 tokens
- 32 lines in 2 placespython199 tokens
- 29 lines in 2 placespython190 tokens
- 29 lines in 2 placespython188 tokens
Largest clones over all files, tests and data included
- 33 lines in 2 placespython359 tokens
238new_motion = np.zeros((n_frames, 1, D), dtype=motion.dtype) 239new_motion[:, 0, 3:9] = motion[:, ji, 3:9] 240 241aug['motion'] = np.concatenate( 242 [motion[:, :ji], new_motion, motion[:, ji:]], axis=1, 243) 244aug['offsets'] = np.concatenate( 245 [offsets[:ji], offset_new[None], offsets[ji:]], axis=0, 246) 247aug['offsets'][ji + 1] = offset_ji_remFirst 10 of 33 lines.
- 40 lines in 2 placespython295 tokensdata_process/motion_rendering/render_mixamo.py:102–141data_process/motion_rendering/render_truebones.py:106–145
102 "mesh_animation/animate_mixamo.py.") 103parser.add_argument("--output_dir", type=str, required=True, 104 help="Output directory.") 105parser.add_argument("--scale", type=float, default=1.0, 106 help="Scene normalization scale.") 107parser.add_argument("--camera_dist", type=float, default=1.5, 108 help="Camera distance from origin.") 109parser.add_argument("--resolution", type=int, default=512, 110 help="Render resolution (square).") 111parser.add_argument("--fps", type=int, default=RENDER_FPS,First 10 of 40 lines.
- 33 lines in 2 placespython248 tokens
147(shift_s, scale_s, gate_s, 148 shift_t, scale_t, gate_t, 149 shift_m, scale_m, gate_m) = self.adaLN_modulation(c).chunk(9, dim=-1) 150 151def expand_to_x(z): 152 return z[:, None, None, :] 153 154use_ckpt = self.gradient_checkpointing and self.training 155 156# spatial attnFirst 10 of 33 lines.
- 8 lines in 3 placespython121 tokens
- 34 lines in 2 placespython240 tokens
By format, code only
| Format | Files | Lines | Clones | Duplicated lines | Duplication |
|---|---|---|---|---|---|
| python | 102 | 35,286 | 108 | 1,500 | 4.25% |
| bash | 39 | 2,489 | 5 | 40 | 1.61% |
| perl | 1 | 174 | 0 | 0 | 0% |
By format, all files
| Format | Files | Lines | Clones | Duplicated lines | Duplication |
|---|---|---|---|---|---|
| python | 102 | 35,286 | 108 | 1,500 | 4.25% |
| json | 9 | 720 | 19 | 550 | 76.39% |
| bash | 41 | 2,587 | 5 | 40 | 1.55% |
| markdown | 2 | 968 | 0 | 0 | 0% |
| perl | 1 | 174 | 0 | 0 | 0% |
| txt | 1 | 89 | 0 | 0 | 0% |
| mermaid | 1 | 31 | 0 | 0 | 0% |
| text | 2 | 24 | 0 | 0 | 0% |
Trending appearances
| Day | Rank | Stars | Files | Lines | Clones | All files | Code | Health | Commit |
|---|---|---|---|---|---|---|---|---|---|
| Oct 2, 2026 | #10 | 1,123 (+217) | 159 | 39,879 | 132 | 5.24% | 4.06% | C 69.3 | 2c5b384 |
Want this for your own project? Install jscpd and run jscpd ., or measure it the way the baselines were measured.