We present videos of four motions along with their original text descriptions and annotator evaluation results. These examples provide insight into how the MotionPercept dataset is annotated and evaluated, as described in Section 3.2 in the paper.
Text description: Warm-up
Annnotation result: C
Text description: Run
Annnotation result: D
Text description: Throw
Annnotation result: C
Text description: Rope-skipping
Annnotation result: A
Text description:Punching
Annnotation result: C
Text description: Left-stretching
Annnotation result: C
Text description: Jump
Annnotation result: B
Text description: Eat
Annnotation result: D
Text description: Throw
Annnotation result: D
Text description: Turn-steering-wheel
Annnotation result: D
This section shows videos of four motions, annotation results, MotionCritic scores, and the values of additional metrics as described in Section 3.3 in the paper.
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -0.7886 | -4.8514 | 0.4993 | -2.0689 |
PFC ↓ | 2.569e-5 | 6.449e-5 | 1.232e-5 | 3.187e-5 |
PoseNDF ↓ | 0.00039 | 0.00060 | 0.00027 | 0.00080 |
Text description: Drink
Annnotation result: C
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -9.1875 | -8.0678 | 4.8846 | 1.4563 |
PFC ↓ | 3.601e-6 | 3.043e-4 | 4.813e-5 | 1.025e-4 |
PoseNDF ↓ | 0.00058 | 0.00051 | 0.00057 | 0.00055 |
Text description: Pulling-chest-expanders
Annnotation result: C
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -4.4318 | -3.4696 | -6.5542 | 2.2963 |
PFC ↓ | 1.045e-3 | 2.793e-4 | 2.975e-4 | 2.958e-4 |
PoseNDF ↓ | 0.00031 | 0.00054 | 0.00049 | 0.00043 |
Text description: Walk
Annnotation result: D
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -2.1850 | 1.5277 | -0.6620 | 3.8842 |
PFC ↓ | 3.111e-5 | 2.580e-5 | 1.903e-4 | 1.165e-5 |
PoseNDF | 0.00064 | 0.00065 | 0.00037 | 0.00073 |
Text description: Boxing
Annnotation result: D
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | 0.8814 | -5.0319 | 0.0365 | 1.3240 |
PFC ↓ | 3.532e-5 | 3.245e-4 | 3.503e-5 | 2.693e-4 |
PoseNDF ↓ | 0.00039 | 0.00042 | 0.00040 | 0.00041 |
Text description: Rotation-clapping
Annnotation result: D
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | 0.6195 | -2.6155 | -2.6123 | -2.1859 |
PFC ↓ | 1.292e-6 | 8.174e-6 | 8.254e-6 | 5.938e-6 |
PoseNDF ↓ | 0.00062 | 0.00107 | 0.00107 | 0.00022 |
Text description: Eat
Annnotation result: A
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -4.3979 | -4.3952 | 0.2009 | -4.4393 |
PFC ↓ | 1.056e-3 | 1.044e-3 | 3.007e-4 | 1.059e-3 |
PoseNDF ↓ | 0.00062 | 0.00107 | 0.00107 | 0.00022 |
Text description: Eat
Annnotation result: C
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -0.9983 | -12.1793 | -3.6499 | -10.8046 |
PFC ↓ | 7.699e-5 | 5.269e-4 | 5.075e-4 | 6.801e-4 |
PoseNDF ↓ | 0.00042 | 0.00052 | 0.00048 | 0.00049 |
Text description: Dumbbell-side-bend
Annnotation result: A
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -7.3115 | -4.5203 | -3.3664 | -0.6248 |
PFC ↓ | 4.820e-5 | 6.480e-5 | 7.905e-5 | 2.555e-5 |
PoseNDF ↓ | 0.00091 | 0.00077 | 0.00056 | 0.00062 |
Text description: Elbow-circling
Annnotation result: D
Metrics | A | B | C | D |
---|---|---|---|---|
Critic score ↑ | -2.8390 | 0.8926 | -4.1106 | -2.1317 |
PFC ↓ | 1.047e-3 | 8.792e-4 | 2.307e-3 | 8.646e-4 |
PoseNDF ↓ | 0.00049 | 0.00059 | 0.00040 | 0.00042 |
Text description: Alternate-knee-lifting
Annnotation result: B
We present video pairs comparing different stages of finetuning, showing the scores provided by MotionCritic and the user preferences collected in the study, as discussed in Section 4 in the paper. This helps confirm the finetuning process through user validation.
Critic score: -13.2
Critic score: -3.79
User preference: step_200
Critic score: 0.995
Critic score: 11.6
User preference: step_600
Critic score: -3.58
Critic score: 1.17
User preference: step_400
Critic score: -3.23
Critic score: 1.49
User preference: step_200
Critic score: -1.05
Critic score: 1.29
User preference: step_400
Critic score: -3.79
Critic score: -0.727
User preference: step_400
Critic score: -2.49
Critic score: -1.79
User preference: step_100
Critic score: -0.761
Critic score: 2.93
User preference: step_300
Critic score: 0.605
Critic score: 1.63
User preference: step_500
Critic score: -0.387
Critic score: 3.45
User preference: step_700
Critic score: -2.70
Critic score: -0.968
User preference: step_200
Critic score: -0.968
Critic score: 0.731
User preference: step_400
Critic score: 0.00632
Critic score: 1.47
User preference: step_800
Critic score: -3.58
Critic score: 4.37
User preference: step_800
Critic score: -4.31
Critic score: -1.05
User preference: step_200
Critic score: 1.294
Critic score: 1.989
User preference: similar
Critic score: 1.989
Critic score: 3.045
User preference: step_800
To demonstrate generalization capablities of MotionCritic, we provide videos from the AMASS ground truth dataset, along with the critic scores assigned, as discussed in Appendix Section B.3. This highlights the performance of MotionCritic even on out-of-distribution motions.
Critic score: -16.789180755615234
Critic score: -12.749826431274414
Critic score: -12.77638053894043
Critic score: -12.838809967041016
Critic score: -13.915456771850586
Critic score: -14.838180541992188
Critic score: -15.517463684082031
Critic score: 10.18864917755127
Critic score: 10.4847993850708
Critic score: 10.672083854675293