UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework

• URL: http://arxiv.org/abs/2512.03918v1
• Date: Wed, 03 Dec 2025 16:03:18 GMT
• Title: UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework
• Abstract summary: We propose UniMo, an autoregressive model for joint modeling of 2D human videos and 3D human motions within a unified framework.<n>We show that our method simultaneously generates corresponding videos and motions while performing accurate motion capture.
• Score: 54.337290937468175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose UniMo, an innovative autoregressive model for joint modeling of 2D human videos and 3D human motions within a unified framework, enabling simultaneous generation and understanding of these two modalities for the first time. Current methods predominantly focus on generating one modality given another as the condition or integrating either of them with other modalities such as text and audio. Unifying 2D videos and 3D motions for simultaneous optimization and generation remains largely unexplored, presenting significant challenges due to their substantial structural and distributional differences. Inspired by the LLM's ability to unify different modalities, our method models videos and 3D motions as a unified tokens sequence, utilizing separate embedding layers to mitigate distribution gaps. Additionally, we devise a sequence modeling strategy that integrates two distinct tasks within a single framework, proving the effectiveness of unified modeling. Moreover, to efficiently align with visual tokens and preserve 3D spatial information, we design a novel 3D motion tokenizer with a temporal expansion strategy, using a single VQ-VAE to produce quantized motion tokens. It features multiple expert decoders that handle body shapes, translation, global orientation, and body poses for reliable 3D motion reconstruction. Extensive experiments demonstrate that our method simultaneously generates corresponding videos and motions while performing accurate motion capture. This work taps into the capacity of LLMs to fuse diverse data types, paving the way for integrating human-centric information into existing models and potentially enabling multimodal, controllable joint modeling of humans, objects, and scenes.

Related papers

• LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models [64.11117186468533]
  World models enable agents to perform forward rollout and planning without real-world interaction.<n>Most existing LAMs rely on single-view inputs and operate primarily in 2D pixel space.<n>We propose LAWM-3D, which introduces three tightly coupled key designs for learning 3D-aware latent actions.
  arXiv  Detail & Related papers  (2026-08-06T07:47:01Z)
• Fine-grained Human Motion Understanding with Language Models [11.539750714535773]
  Methodname represents motion as a sequence of skeletal poses with explicit timestamps for each pose.<n>We construct a training mixture spanning pose captioning, pose question answering, motion captioning, and motion question answering.<n>Our approach supports both 2D and 3D skeletal motion representations through a unified pose encoder.
  arXiv  Detail & Related papers  (2026-06-18T19:31:56Z)
• MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes [52.45449797329548]
  MotionDreamer is a diffusion-based framework for category-agnostic skeletal animation generation from 2D video guidance.<n>We propose a structural-semantic injection mechanism to bridge the gap between 2D visual motion cues and heterogeneous 3D skeletal structures.<n>Our approach significantly outperforms existing methods, setting a new state-of-the-art benchmark for robust and efficient 4D asset generation.
  arXiv  Detail & Related papers  (2026-06-01T00:42:31Z)
• EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer [64.69014756863331]
  We introduce EchoMotion, a framework designed to model the joint distribution of appearance and human motion.<n>We also propose MVS-RoPE, which offers unified 3D positional encoding for both video and motion tokens.<n>Our findings reveal that explicitly representing human motion is to appearance, significantly boosting the coherence and plausibility of human-centric video generation.
  arXiv  Detail & Related papers  (2025-12-21T17:08:14Z)
• Puppeteer: Rig and Animate Your 3D Models [105.11046762553121]
  Puppeteer is a comprehensive framework that addresses both automatic rigging and animation for diverse 3D objects.<n>Our system first predicts plausible skeletal structures via an auto-regressive transformer.<n>It then infers skinning weights via an attention-based architecture.
  arXiv  Detail & Related papers  (2025-08-14T17:59:31Z)
• SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios [48.09735396455107]
  Hand-Object Interaction (HOI) generation has significant application potential.<n>Current 3D HOI motion generation approaches heavily rely on predefined 3D object models and lab-captured motion data.<n>We propose a novel framework that combines visual priors and dynamic constraints within a synchronized diffusion process to generate the HOI video and motion simultaneously.
  arXiv  Detail & Related papers  (2025-06-03T05:04:29Z)
• Zero-Shot Human-Object Interaction Synthesis with Multimodal Priors [31.277540988829976]
  This paper proposes a novel zero-shot HOI synthesis framework without relying on end-to-end training on currently limited 3D HOI datasets.<n>We employ pre-trained human pose estimation models to extract human poses and introduce a generalizable category-level 6-DoF estimation method to obtain the object poses from 2D HOI images.
  arXiv  Detail & Related papers  (2025-03-25T23:55:47Z)
• Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining [49.223455189395025]
  Mocap-2-to-3 is a novel framework that performs multi-view lifting from monocular input.<n>To leverage abundant 2D data, we decompose complex 3D motion into multi-view syntheses.<n>Our method surpasses state-of-the-art approaches in both camera-space motion realism and world-grounded human positioning.
  arXiv  Detail & Related papers  (2025-03-05T06:32:49Z)
• Realistic Human Motion Generation with Cross-Diffusion Models [30.854425772128568]
  Cross Human Motion Diffusion Model (CrossDiff) Method integrates 3D and 2D information using a shared transformer network within the training of the diffusion model. CrossDiff effectively combines the strengths of both representations to generate more realistic motion sequences.
  arXiv  Detail & Related papers  (2023-12-18T07:44:40Z)
• MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion [57.90404618420159]
  We introduce Multi-view Ancestral Sampling (MAS), a method for 3D motion generation. MAS works by simultaneously denoising multiple 2D motion sequences representing different views of the same 3D motion. We demonstrate MAS on 2D pose data acquired from videos depicting professional basketball maneuvers.
  arXiv  Detail & Related papers  (2023-10-23T09:05:18Z)
• Human Performance Capture from Monocular Video in the Wild [50.34917313325813]
  We propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses. Our method outperforms state-of-the-art methods on an in-the-wild human video dataset 3DPW.
  arXiv  Detail & Related papers  (2021-11-29T16:32:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.