Realistic Human Motion Generation with Cross-Diffusion Models
- URL: http://arxiv.org/abs/2312.10993v3
- Date: Mon, 5 Aug 2024 01:58:58 GMT
- Title: Realistic Human Motion Generation with Cross-Diffusion Models
- Authors: Zeping Ren, Shaoli Huang, Xiu Li,
- Abstract summary: 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.
- Score: 30.854425772128568
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce the Cross Human Motion Diffusion Model (CrossDiff), a novel approach for generating high-quality human motion based on textual descriptions. Our method integrates 3D and 2D information using a shared transformer network within the training of the diffusion model, unifying motion noise into a single feature space. This enables cross-decoding of features into both 3D and 2D motion representations, regardless of their original dimension. The primary advantage of CrossDiff is its cross-diffusion mechanism, which allows the model to reverse either 2D or 3D noise into clean motion during training. This capability leverages the complementary information in both motion representations, capturing intricate human movement details often missed by models relying solely on 3D information. Consequently, CrossDiff effectively combines the strengths of both representations to generate more realistic motion sequences. In our experiments, our model demonstrates competitive state-of-the-art performance on text-to-motion benchmarks. Moreover, our method consistently provides enhanced motion generation quality, capturing complex full-body movement intricacies. Additionally, with a pretrained model,our approach accommodates using in the wild 2D motion data without 3D motion ground truth during training to generate 3D motion, highlighting its potential for broader applications and efficient use of available data resources. Project page: https://wonderno.github.io/CrossDiff-webpage/.
Related papers
- Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text [61.9973218744157]
We introduce Director3D, a robust open-world text-to-3D generation framework, designed to generate both real-world 3D scenes and adaptive camera trajectories.
Experiments demonstrate that Director3D outperforms existing methods, offering superior performance in real-world 3D generation.
arXiv Detail & Related papers (2024-06-25T14:42:51Z) - Investigating the impact of 2D gesture representation on co-speech gesture generation [5.408549711581793]
We evaluate the impact of the dimensionality of the training data, 2D or 3D joint coordinates, on the performance of a multimodal speech-to-gesture deep generative model.
arXiv Detail & Related papers (2024-06-21T12:59:20Z) - Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment [45.74813582690906]
Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics.
We present the Video-to-Motion Generator (VTM), which leverages motion priors through cross-modal latent feature space alignment.
The VTM showcases state-of-the-art performance in reconstructing 3D human motion from monocular videos.
arXiv Detail & Related papers (2024-04-15T06:38:09Z) - GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians [51.46168990249278]
We present an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video.
GustafAvatar is validated on both the public dataset and our collected dataset.
arXiv Detail & Related papers (2023-12-04T18:55:45Z) - X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation [61.48050470095969]
X-Dreamer is a novel approach for high-quality text-to-3D content creation.
It bridges the gap between text-to-2D and text-to-3D synthesis.
arXiv Detail & Related papers (2023-11-30T07:23:00Z) - 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) - MoDA: Modeling Deformable 3D Objects from Casual Videos [84.29654142118018]
We propose neural dual quaternion blend skinning (NeuDBS) to achieve 3D point deformation without skin-collapsing artifacts.
In the endeavor to register 2D pixels across different frames, we establish a correspondence between canonical feature embeddings that encodes 3D points within the canonical space.
Our approach can reconstruct 3D models for humans and animals with better qualitative and quantitative performance than state-of-the-art methods.
arXiv Detail & Related papers (2023-04-17T13:49:04Z) - MotionBERT: A Unified Perspective on Learning Human Motion
Representations [46.67364057245364]
We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources.
We propose a pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations.
We implement motion encoder with a Dual-stream Spatio-temporal Transformer (DSTformer) neural network.
arXiv Detail & Related papers (2022-10-12T19:46:25Z) - MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks [77.56526918859345]
We present a novel framework that brings the 3D motion task from controlled environments to in-the-wild scenarios.
It is capable of body motion from a character in a 2D monocular video to a 3D character without using any motion capture system or 3D reconstruction procedure.
arXiv Detail & Related papers (2021-12-19T07:52:05Z) - Action2video: Generating Videos of Human 3D Actions [31.665831044217363]
We aim to tackle the interesting yet challenging problem of generating videos of diverse and natural human motions from prescribed action categories.
Key issue lies in the ability to synthesize multiple distinct motion sequences that are realistic in their visual appearances.
Action2motionally generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos.
arXiv Detail & Related papers (2021-11-12T20:20:37Z)
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.