SOTAVerified

Motion Synthesis

Creating a video where people in the images move (such as blinking or smiling) requires specialized AI technology like Deepfake or Motion Synthesis, which I cannot do directly here.

However, if you want a video made from the images you provided, I can create an animated slideshow with cute effects and royalty-free background music. Would you be interested in this?

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 282 papers

TitleStatusHype
DeepGesture: A conversational gesture synthesis system based on emotions and semanticsCode0
VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and CollisionsCode2
DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked ModelingCode1
PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis—0
Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation—0
DanceChat: Large Language Model-Guided Music-to-Dance Generation—0
MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation—0
MotionPro: A Precise Motion Controller for Image-to-Video Generation—0
One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion—0
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes—0
Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion—0
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis—0
Text-driven Motion Generation: Overview, Challenges and Directions—0
M3G: Multi-Granular Gesture Generator for Audio-Driven Full-Body Human Motion Synthesis—0
Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis—0
Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion—0
Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation—0
Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future DirectionsCode2
Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis—0
MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer—0
DanceMosaic: High-Fidelity Dance Generation with Multimodal Editability—0
Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions—0
DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance—0
FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation—0
Articulated Kinematics Distillation from Video Diffusion Models—0
ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer—0
StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion—0
Target-Aware Video Diffusion Models—0
Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor controlCode2
Motion Synthesis with Sparse and Flexible Keyjoint Control—0
Less is More: Improving Motion Diffusion Models with Sparse Keyframes—0
PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data—0
Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion—0
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion ModelsCode1
Motion Anything: Any to Motion GenerationCode3
Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction—0
BioMoDiffuse: Physics-Guided Biomechanical Diffusion for Controllable and Authentic Human Motion Synthesis—0
Riemann^2: Learning Riemannian Submanifolds from Riemannian Data—0
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects—0
Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis—0
Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis—0
Human Motion Prediction, Reconstruction, and Generation—0
SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion—0
FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis—0
MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model—0
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency LossCode2
FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation—0
KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained AlignmentCode0
LS-GAN: Human Motion Synthesis with Latent-space GANs—0
SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis—0
Show:102550
← PrevPage 1 of 6Next →
All datasetsHumanML3DKIT Motion-LanguageAIST++InterHumanFineDanceInter-XAIOZ-GDANCELaFAN1Motion-XBRACEHumanAct12TMD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Language2PoseFID11.02—Unverified
2Diffuion MotionFID10.21—Unverified
3Text2GestureFID5.01—Unverified
4TM2TFID1.5—Unverified
5T2MFID1.09—Unverified
6TM2D (t2m)FID1.02—Unverified
7MAAFID0.77—Unverified
8MotionDiffuseFID0.63—Unverified
9MDMFID0.54—Unverified
10MLDFID0.47—Unverified
#ModelMetricClaimedVerifiedStatus
1Text2GestureFID12.12—Unverified
2Language2PoseFID6.55—Unverified
3TEMOSFID3.72—Unverified
4TM2TFID3.6—Unverified
5T2MFID3.02—Unverified
6MotionDiffuseFID1.95—Unverified
7AttT2MFID0.87—Unverified
8T2M-GPT (τ = 0)FID0.74—Unverified
9T2M-GPT (τ = 0.5)FID0.72—Unverified
10Fg-T2MFID0.57—Unverified
#ModelMetricClaimedVerifiedStatus
1Dance RevolutionFID73.42—Unverified
2DanceNetFID69.13—Unverified
3MoFusionFID50.31—Unverified
4Lodge (DDPM)FID37.09—Unverified
5AI ChoreographerFID35.35—Unverified
6BailandoFID28.16—Unverified
7TM2D (only motion data)FID23.94—Unverified
8TM2DFID19.01—Unverified
9UDEFID17.25—Unverified
10Motion AnythingFID17.22—Unverified
#ModelMetricClaimedVerifiedStatus
1TEMOSFID17.38—Unverified
2T2MFID13.77—Unverified
3MDMFID9.17—Unverified
4ComMDMFID7.07—Unverified
5RIGFID6.78—Unverified
6FreeMotionFID6.74—Unverified
7InterGenFID5.92—Unverified
8MoMat-MoGenFID5.67—Unverified
9in2INFID5.18—Unverified
10InterMaskFID5.15—Unverified
#ModelMetricClaimedVerifiedStatus
1FACTfid_k113.38—Unverified
2MNETfid_k104.71—Unverified
3EDGEfid_k94.34—Unverified
4Bailandofid_k82.81—Unverified
5Lodge (DDIM)fid_k50—Unverified
6Lodge (DDPM)fid_k45.56—Unverified
7Lodge++fid_k40.77—Unverified
8DanceMosaicfid_k19.36—Unverified
#ModelMetricClaimedVerifiedStatus
1ComMDMFID29.27—Unverified
2TEMOSFID29.26—Unverified
3MDMFID23.7—Unverified
4T2MFID5.48—Unverified
5InterGenFID5.21—Unverified
6InterMaskFID0.4—Unverified
#ModelMetricClaimedVerifiedStatus
1GDANCERFID43.9—Unverified
2TCDiffFID42.39—Unverified
3GCDFID31.16—Unverified
4Scalable Group ChoreographyFID31.01—Unverified
#ModelMetricClaimedVerifiedStatus
1HM-VAEL2Q@50.24—Unverified
2TG-completeL2Q@50.17—Unverified
3SSMCTL2Q@50.14—Unverified
4-interpolatorL2Q@50.11—Unverified
#ModelMetricClaimedVerifiedStatus
1MDMFID3.8—Unverified
2MLDFID3.41—Unverified
3T2M-GPTFID1.37—Unverified
4HumanTOMATOFID1.17—Unverified
#ModelMetricClaimedVerifiedStatus
1Dancing 2 MusicFrechet Inception Distance0.59—Unverified
2AIST++Frechet Inception Distance0.57—Unverified
3Dance RevolutionFrechet Inception Distance0.52—Unverified
#ModelMetricClaimedVerifiedStatus
1MDMAccuracy0.99—Unverified
2MLDAccuracy0.96—Unverified
#ModelMetricClaimedVerifiedStatus
1Motion AnythingFID21.46—Unverified
#ModelMetricClaimedVerifiedStatus
1Match-TTSGMean Opinion Score3.44—Unverified