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 101–150 of 282 papers

TitleStatusHype
Point-Based Radiance Fields for Controllable Human Motion SynthesisCode1
Constrained Synthesis with Projected Diffusion ModelsCode1
ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person InteractionsCode1
Residual Force Control for Agile Human Behavior Imitation and Extended Motion SynthesisCode1
Role-Aware Interaction Generation from Textual DescriptionCode1
Self-Correcting Self-Consuming Loops for Generative Model TrainingCode1
Single-Shot Motion Completion with TransformerCode1
Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweeningCode1
Style-Controllable Speech-Driven Gesture Synthesis Using Normalising FlowsCode1
Synthesis of Compositional Animations from Textual DescriptionsCode1
Synthesizing Long-Term 3D Human Motion and Interaction in 3D ScenesCode1
T3M: Text Guided 3D Human Motion Synthesis from SpeechCode1
TM2D: Bimodality Driven 3D Dance Generation via Music-Text IntegrationCode1
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and TextsCode1
UDE: A Unified Driving Engine for Human Motion GenerationCode1
Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic ModelsCode1
DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control—0
I2VControl: Disentangled and Unified Video Motion Synthesis Control—0
Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion—0
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes—0
DanceMosaic: High-Fidelity Dance Generation with Multimodal Editability—0
Infinite Motion: Extended Motion Generation via Long Text Instructions—0
StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion—0
Cross-Conditioned Recurrent Networks for Long-Term Synthesis of Inter-Person Human Motion Interactions—0
Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models—0
SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis—0
Contact-aware Human Motion Generation from Textual Descriptions—0
It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model—0
Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis—0
GlocalNet: Class-aware Long-term Human Motion Synthesis—0
Guided Motion Diffusion for Controllable Human Motion Synthesis—0
Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models—0
Harmonious Group Choreography with Trajectory-Controllable Diffusion—0
Hierarchical Style-based Networks for Motion Synthesis—0
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects—0
Decoupling Training-Free Guided Diffusion by ADMM—0
Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text—0
Human Motion Prediction, Reconstruction, and Generation—0
Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning—0
KinMo: Kinematic-aware Human Motion Understanding and Generation—0
Synthesising 3D Facial Motion from "In-the-Wild" Speech—0
LEAD: Latent Realignment for Human Motion Diffusion—0
Unimotion: Unifying 3D Human Motion Synthesis and Understanding—0
Learning to Generate Diverse Dance Motions with Transformer—0
Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control—0
Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction—0
Analysis of Co-Laughter Gesture Relationship on RGB Videos in Dyadic Conversation Context—0
Less is More: Improving Motion Diffusion Models with Sparse Keyframes—0
UNOC: Understanding Occlusion for Embodied Presence in Virtual Reality—0
Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation—0
Show:102550
← PrevPage 3 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