Gesture Generation
34 papers with code • 4 benchmarks • 6 datasets
Generation of gestures, as a sequence of 3d poses
Libraries
Use these libraries to find Gesture Generation models and implementations
DVS128 Gesture
BEAT
BEAT2
Most implemented papers
Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows
simonalexanderson/StyleGestures
•
•
Computer Graphics Forum 2020
In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters.
Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation
GestureGeneration/Speech_driven_gesture_generation_with_autoencoder
•
•
We provide an analysis of different representations for the input (speech) and the output (motion) of the network by both objective and subjective evaluations.
Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach
chahuja/mix-stage
•
•
ECCV 2020
A key challenge, called gesture style transfer, is to learn a model that generates these gestures for a speaking agent 'A' in the gesturing style of a target speaker 'B'.
No Gestures Left Behind: Learning Relationships between Spoken Language and Freeform Gestures
chahuja/aisle
•
•
Findings of the Association for Computational Linguistics 2020
We study relationships between spoken language and co-speech gestures in context of two key challenges.
DeepNAG: Deep Non-Adversarial Gesture Generation
Maghoumi/DeepNAG
•
•
We find that DeepNAG outperforms DeepGAN in accuracy, training time (up to 17x faster), and realism, thereby opening the door to a new line of research in generator network design and training for gesture synthesis.
A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
To date, recent end-to-end gesture generation methods have not been evaluated in a real-time interaction with users.
Probabilistic Human-like Gesture Synthesis from Speech using GRU-based WGAN
wubowen416/gesture-generation
•
•
ACM ICMI Workshop GENEA 2021
The motions synthesized by the proposed system are evaluated via an objective measure and a subjective experiment, showing that the proposed model outperforms a baseline model which is trained by a state-of-the-art GAN-based algorithm, using the same dataset.
Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning
UttaranB127/speech2affective_gestures
•
•
Our network consists of two components: a generator to synthesize gestures from a joint embedding space of features encoded from the input speech and the seed poses, and a discriminator to distinguish between the synthesized pose sequences and real 3D pose sequences.
Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates
shenhanqian/speechdrivestemplates
•
•
ICCV 2021
Co-speech gesture generation is to synthesize a gesture sequence that not only looks real but also matches with the input speech audio.
Gesture2Vec: Clustering Gestures using Representation Learning Methods for Co-speech Gesture Generation
We propose a vector-quantized variational autoencoder structure as well as training techniques to learn a rigorous representation of gesture sequences.
