HumanML3D
PulseAugur coverage of HumanML3D — every cluster mentioning HumanML3D across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
WaMo framework enhances text-motion retrieval with wavelet analysis · arXiv cs.CV
Researchers have developed WaMo, a new framework for text-motion retrieval that uses wavelet decomposition to analyze 3D motion sequences. This method captures joint-specific and time-varying motion details at multiple …
-
MUGEN framework unifies motion understanding and generation with continuous latents
Researchers have introduced MUGEN, a novel unified framework designed for efficient motion understanding and generation. Unlike previous methods that rely on discrete motion codebooks, MUGEN utilizes a single draw from …
-
New framework KineMIC enhances few-shot action synthesis for HAR
Researchers have developed KineMIC, a novel transfer learning framework designed to improve few-shot action synthesis for skeletal-based Human Activity Recognition (HAR). This method adapts text-to-motion diffusion mode…
-
ScaleMoGen framework advances text-driven human motion generation
Researchers have introduced ScaleMoGen, a novel framework for generating human motion from text descriptions. This approach utilizes an autoregressive method that predicts motion tokens across multiple scales, from coar…
-
New research refines diffusion model noise for better video generation control
Two new research papers propose novel methods for improving controllability in diffusion-based video generation by manipulating the initial noise input. The first paper, WINRO, focuses on text-to-motion generation by re…
-
New Transformer Tokenizer Uses Language to Improve Human Motion Generation
Researchers have developed a novel Language-Guided Tokenizer (LG-Tok) for generating human motion, which converts raw motion data into compact, semantically rich tokens. This method uses a Transformer-based tokenizer to…
-
New research tackles articulated object motion generation and modeling
Two new research papers, PWM-ArtGen and SAMoR, introduce novel approaches to generating and modeling motion for articulated objects. PWM-ArtGen focuses on predicting the kinematic structure of objects from a single imag…
-
New research tackles diffusion model efficiency and applications · 8 sources tracked
Recent research explores advancements in diffusion models, focusing on improving their efficiency and applicability across various domains. FlashDiff introduces adaptive regional execution and scheduling to reduce servi…
-
New LoRA variants enhance continual learning for motion-language agents
Researchers have developed new Low-Rank Adaptation (LoRA) variants to improve the continual learning capabilities of motion-language agents. These agents need to understand and generate human movement from text without …
-
New DC-Motion Framework Generates Realistic Human Motion from Text
Researchers have developed DC-Motion, a novel framework for generating human motion from text. This approach decouples semantic meaning from fine-grained physical details using a combination of discrete and continuous t…
-
VideoMDM generates 3D human motion from 2D video without 3D ground truth
Researchers have developed VideoMDM, a novel diffusion-based framework for generating 3D human motion from 2D video supervision. This method trains 3D motion priors directly from 2D poses, bypassing the need for explici…
-
New method converts human motion to text for LLM analysis
Researchers have developed a new method called Structured Motion Description (SMD) that converts human motion data into natural language text. This approach bypasses the need for specialized encoders by representing joi…
-
New AI models generate realistic human motion with precise trajectory control
Researchers have developed new methods for generating realistic human motion that accurately follows specified trajectories and textual descriptions. One approach, CMC, uses a two-stage diffusion process to first ensure…
-
New method generates stylized human motion from text using hypernetworks
Researchers have developed a novel framework for generating stylized human motions from text descriptions, addressing limitations in current text-to-motion models. Their approach utilizes a hypernetwork to dynamically a…
-
New AI models generate high-quality 3D human motion in real-time
Researchers have developed new transformer-based frameworks for generating high-quality 3D human motion from text. MOGO utilizes a hierarchical vector quantization and a single-pass causal transformer for real-time gene…
-
New method uses LLMs for encoder-free human motion understanding
Researchers have developed a novel method called Structured Motion Description (SMD) for understanding human motion using large language models (LLMs). Unlike previous approaches that required dedicated encoders to alig…