Motion Synthesis

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

13 leaderboard tables shown for this task, 13 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 13 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

19 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 126 papers with code (282 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• On human motion prediction using recurrent neural networks
  6 May 2017 8 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 3 pointer-only (licence)
  Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented…
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
  8 Apr 2018 6 repositories listed
  We further explore a number of methods for integrating multiple clips into the learning process to develop multi-skilled agents capable of performing a rich repertoire of diverse skills.
• Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels
  15 Nov 2021 3 repositories listed
  In this work, we follow the trend of rendering the NIMAT effect by introducing a modification on the blur synthesis procedure in portrait mode.
• MoGlow: Probabilistic and controllable motion synthesis using normalising flows
  16 May 2019 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  Data-driven modelling and synthesis of motion is an active research area with applications that include animation, games, and social robotics.
• HP-GAN: Probabilistic 3D human motion prediction via GAN
  27 Nov 2017 3 repositories listed
  Our model, which we call HP-GAN, learns a probability density function of future human poses conditioned on previous poses.
• AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
  11 Mar 2025 2 repositories listed
  Despite recent advancements in learning-based motion in-betweening, a key limitation has been overlooked: the requirement for character-specific datasets.
• MotionClone: Training-Free Motion Cloning for Controllable Video Generation
  8 Jun 2024 2 repositories listed Syntology ran 6 of 15 samples · 9 unverified · 15 pointer-only (licence)
  Motion-based controllable video generation offers the potential for creating captivating visual content.
• Human Motion Diffusion as a Generative Prior
  2 Mar 2023 2 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 2 pointer-only (licence)
  We evaluate the composition methods using an off-the-shelf motion diffusion model, and further compare the results to dedicated models trained for these specific tasks.
• MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
  31 Aug 2022 2 repositories listed
  Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected.
• MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
  16 Apr 2021 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  To improve upon existing models, we propose a generic audio-driven facial animation approach that achieves highly realistic motion synthesis results for the entire face.
• Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
  12 Apr 2021 2 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action.
• Dancing to Music
  5 Nov 2019 2 repositories listed
  In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move.
• DeepGesture: A conversational gesture synthesis system based on emotions and semantics
  3 Jul 2025 1 repository listed
  Along with the explosion of large language models, improvements in speech synthesis, advancements in hardware, and the evolution of computer graphics, the current bottleneck in creating digital humans lies in generating…
• VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions
  29 Jun 2025 1 repository listed
  Parametric human body models play a crucial role in computer graphics and vision, enabling applications ranging from human motion analysis to understanding human-environment interactions.
• DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling
  23 Jun 2025 1 repository listed
  Subsequently, in the second stage, two generative masked transformers learn to map music signals to these dance tokens: the first producing high-level semantic tokens, and the second, conditioned on music and these…
• Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions
  27 Apr 2025 1 repository listed
  This survey is intended as a resource for researchers and developers entering the field of generative AI animation or adjacent fields.
• Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control
  18 Mar 2025 1 repository listed
  In this work, we present a model-free motion imitation framework (KINESIS) to advance the understanding of muscle-based motor control.
• Motion Anything: Any to Motion Generation
  10 Mar 2025 1 repository listed
  Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain.
• Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss
  30 Jan 2025 1 repository listed
  Rapid progress in text-to-motion generation has been largely driven by diffusion models.
• KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment
  25 Jan 2025 1 repository listed
  Among the various conditions of motion generation, text can describe motion details elaborately and is easy to acquire, making text-to-motion(T2M) generation important.
• MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension
  26 Nov 2024 1 repository listed
  This paper introduces MotionLLaMA, a unified framework for motion synthesis and comprehension, along with a novel full-body motion tokenizer called the HoMi Tokenizer.
• Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
  31 Oct 2024 1 repository listed Syntology ran 0 of 11 samples · 11 unverified
  This issue stems from the internal biases in text encoding, which overlooks motions, and inadequate conditioning mechanisms in T2V generation models.
• Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
  14 Oct 2024 1 repository listed Syntology ran 4 of 6 samples · 2 unverified
  Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of…
• InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling
  13 Oct 2024 1 repository listed
  In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space.
• BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation
  17 Sep 2024 1 repository listed
  Autoregressive models excel in modeling sequential dependencies by enforcing causal constraints, yet they struggle to capture complex bidirectional patterns due to their unidirectional nature.
• LawDNet: Enhanced Audio-Driven Lip Synthesis via Local Affine Warping Deformation
  14 Sep 2024 1 repository listed
  In the domain of photorealistic avatar generation, the fidelity of audio-driven lip motion synthesis is essential for realistic virtual interactions.
• T3M: Text Guided 3D Human Motion Synthesis from Speech
  23 Aug 2024 1 repository listed
  Speech-driven 3D motion synthesis seeks to create lifelike animations based on human speech, with potential uses in virtual reality, gaming, and the film production.
• MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls
  30 Jul 2024 1 repository listed
  However, employing a unified model to achieve various generation tasks with different condition modalities presents two main challenges: motion distribution drifts across different tasks (e.
• Length-Aware Motion Synthesis via Latent Diffusion
  16 Jul 2024 1 repository listed
  The target duration of a synthesized human motion is a critical attribute that requires modeling control over the motion dynamics and style.
• Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer
  10 Jun 2024 1 repository listed
  Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing?

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.