HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesÉvénementsWikiSOTAModèles LLM
Recherche
À propos
HyperAI

3D Human Pose Estimation On Mpi Inf 3Dhp

Métriques

MPJPE
PCK

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif
Nom du modèleMPJPEPCK
canonpose-self-supervised-monocular-3d-human10477
3d-human-pose-estimation-in-the-wild-by-69.0
spatio-temporal-tendency-reasoning-for-human95.3-
graph-stacked-hourglass-networks-for-3d-human-80.1
deep-two-stream-video-inference-for-human93.4-
mixste-seq2seq-mixed-spatio-temporal-encoder54.994.4
probabilistic-monocular-3d-human-pose-84.3
self-attentive-3d-human-pose-and-shape94.390.1
ponet-robust-3d-human-pose-estimation-via115.076.1
posetriplet-co-evolving-3d-human-pose79.589.1
crossformer-cross-spatio-temporal-transformer76.389.1
weakly-supervised-3d-human-pose-learning-via110.880.2
srnet-improving-generalization-in-3d-human-77.6
repnet-weakly-supervised-training-of-an92.581.8
absposelifter-absolute-3d-human-pose-lifting-84
3d-human-pose-estimation-with-spatial-and77.188.6
3d-human-pose-estimation-with-spatio-temporal23.198.7
w-hmr-human-mesh-recovery-in-world-space-with83.2-
fusionformer-exploiting-the-joint-motion28.297.9
finepose-fine-grained-prompt-driven-3d-human26.298.9
vnect-real-time-3d-human-pose-estimation-with-79.4
vnect-real-time-3d-human-pose-estimation-with124.776.6
leveraging-mocap-data-for-human-mesh-recovery97.4-
capturing-humans-in-motion-temporal-attentive96.7-
learning-temporal-3d-human-pose-estimation93.081.0
posegu-3d-human-pose-estimation-with-novel79.186.3
beyond-static-features-for-temporally97.4-
ddt-a-diffusion-driven-transformer-based97.8-
generating-multiple-hypotheses-for-3d-human-67.9
predicting-camera-viewpoint-improves-cross90.384.3
learnable-human-mesh-triangulation-for-3d33.799.37
hybrik-a-hybrid-analytical-neural-inverse91.087.5
motionagformer-enhancing-3d-human-pose16.298.2
beyond-static-features-for-temporally97.3-
3d-human-motion-estimation-via-motion96.4-
unsupervised-3d-pose-estimation-with-71.1
motion-guided-3d-pose-estimation-from-videos68.186.9
poseaug-a-differentiable-pose-augmentation71.189.2
end-to-end-recovery-of-human-shape-and-pose124.272.9
learnable-human-mesh-triangulation-for-3d45.8796.59
consensus-based-optimization-for-3d-human112.180.6
convformer-parameter-reduction-in-transformer53.696.4
motionagformer-enhancing-3d-human-pose19.298.2
weakly-supervised-generative-network-for-79.3
diffusion-based-3d-human-pose-estimation-with29.797.7
staf-3d-human-mesh-recovery-from-video-with92.4-
arts-semi-analytical-regressor-using71.8-
hstformer-hierarchical-spatial-temporal28.398
monocular-3d-human-pose-estimation-in-the-64.7
repnet-weakly-supervised-training-of-an97.882.5
mixste-seq2seq-mixed-spatio-temporal-encoder57.994.2
learning-skeletal-graph-neural-networks-for-82.1
global-to-local-modeling-for-video-based-3d93.9-
3d-human-pose-estimation-using-spatio-1-84.1
orinet-a-fully-convolutional-network-for-3d-64.6
ordinal-depth-supervision-for-3d-human-pose-71.9
conditional-directed-graph-convolution-for-3d42.597.9
global-adaptation-meets-local-generalization61.392.1
metrabs-metric-scale-truncation-robust74.9±1.490.6±0.4
tcpformer-learning-temporal-correlation-with17.898.7
encoder-decoder-with-multi-level-attention83.6-
poseformerv2-exploring-frequency-domain-for27.897.9
poseaug-a-differentiable-pose-augmentation76.6-
context-modeling-in-3d-human-pose-estimation-80.5
modulated-graph-convolutional-network-for-3d-86.1
ktpformer-kinematics-and-trajectory-prior16.798.9
dc-gnet-deep-mesh-relation-capturing-graph97.2-
3d-human-pose-estimation-via-explicit-93.2
3d-human-shape-and-pose-from-a-single-low103.36-
hybrik-x-hybrid-analytical-neural-inverse9187.1
exemplar-fine-tuning-for-3d-human-pose--
htnet-human-topology-aware-network-for-3d-86.7
mhformer-multi-hypothesis-transformer-for-3d5893.8
tcpformer-learning-temporal-correlation-with1599.0
back-to-optimization-diffusion-based-zero55.293
trajectory-space-factorization-for-deep-video79.883.6
learning-to-reconstruct-3d-human-pose-and-92.5
ssp-net-scalable-sequential-pyramid-networks96.883.2
motionagformer-enhancing-3d-human-pose18.298.3
anatomy-aware-3d-human-pose-estimation-in79.187.8
learning-to-regress-bodies-from-images-using-1104.7-
double-chain-constraints-for-3d-human-pose-87.5
denserac-joint-3d-pose-and-shape-estimation114.276.9
learning-to-reconstruct-3d-human-pose-and105.276.4
xformer-fast-and-accurate-monocular-3d-body109.8-
poseaug-a-differentiable-pose-augmentation7388.6
refined-temporal-pyramidal-compression-and40.598.8
single-shot-multi-person-3d-pose-estimation122.275.2
p-stmo-pre-trained-spatial-temporal-many-to32.297.9
live-stream-temporally-embedded-3d-human-body96.2-
ikol-inverse-kinematics-optimization-layer88.887.9
hybrik-transformer86.288.6
monocular-3d-human-pose-estimation-in-the117.675.7
tape-temporal-attention-based-probabilistic94-
hemlets-pose-learning-part-centric-heatmap-1-75.3
pliks-a-pseudo-linear-inverse-kinematic67.6-
generalizing-monocular-3d-human-pose-71.2
poseaug-a-differentiable-pose-augmentation73.2-
cascaded-deep-monocular-3d-human-pose-199.781.2
ray3d-ray-based-3d-human-pose-estimation-for46.6-
gla-gcn-global-local-adaptive-graph27.7698.53
learning-dynamical-human-joint-affinity-for76-
diffpose-toward-more-reliable-3d-pose29.198
temporal-aware-refinement-for-video-based85.9-
teaching-independent-parts-separately-tips-78
anatomy-aware-3d-human-pose-estimation-in78.887.9
hierarchical-graph-networks-for-3d-human-pose-85.2
self-supervised-learning-of-3d-human-pose108.9977.5
regular-splitting-graph-network-for-3d-human-85.6
out-of-domain-human-mesh-reconstruction-via101.579.5
motionagformer-enhancing-3d-human-pose17.198.3
3d-human-pose-estimation-with-2d-marginal91.385.4
posenet3d-unsupervised-3d-human-shape-and102.481.9
xnect-real-time-multi-person-3d-human-pose98.482.8
vibe-video-inference-for-human-body-pose-and96.689.3
learning-local-recurrent-models-for-human94.6-