paper-with-me

Papers

InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling

2024-10-13 · Muhammad Gohar Javed, Chuan Guo, Li Cheng, Xingyu Li

Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often generate unnatural and unrealistic results. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each token. Building on this representation, InterMask utilizes a generative masked modeling framework to collaboratively model the tokens of two interacting individuals. This is achieved by employing a transformer architecture specifically designed to capture complex spatio-temporal interdependencies. During training, it randomly masks the motion tokens of both individuals and learns to predict them. In inference, starting from fully masked sequences, it progressively fills in the tokens for both individuals. With its enhanced motion representation, dedicated architecture, and effective learning strategy, InterMask achieves state-of-the-art results, producing high-fidelity and diverse human interactions. It outperforms previous methods, achieving an FID of $5.154$ (vs $5.535$ for in2IN) on the InterHuman dataset and $0.399$ (vs $5.207$ for InterGen) on the InterX dataset. Additionally, InterMask seamlessly supports reaction generation without the need for model redesign or fine-tuning.

📄 PDF Abstract BibTeX arXiv:2410.10010

Code (1)

gohar-malik/intermask 공식 구현 pytorch

Tasks

Motion Synthesis

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음

Similar Papers 제목 키워드 기반

COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models

2024-09-30 · Divyanshu Daiya, Damon Conover, Aniket Bera

We propose a novel framework COLLAGE for generating collaborative agent-object-agent interactions by leveraging large language models (LLMs) and hierarchical motion-specific vector-quantized variational autoencoders (VQ-…

DenoisingDiversityMotion GenerationMotion Planning

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

2024-06-27 · CVPR 2025 1 · Yun Liu, Chengwen Zhang, Ruofan Xing, Bingda Tang 외

Understanding how humans cooperatively rearrange household objects is critical for VR/AR and human-robot interaction. However, in-depth studies on modeling these behaviors are under-researched due to the lack of relevant…

Human-Object Interaction DetectionHuman-Object Interaction GenerationMotion ForecastingObject+1

Human-Robot Collaboration via Deep Reinforcement Learning of Real-World Interactions

2019-12-02 · Jonas Tjomsland, Ali Shafti, A. Aldo Faisal

We present a robotic setup for real-world testing and evaluation of human-robot and human-human collaborative learning. Leveraging the sample-efficiency of the Soft Actor-Critic algorithm, we have implemented a robotic p…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems

2023-10-13 · Junjie Zhang, Yupeng Hou, Ruobing Xie, Wenqi Sun 외

Recently, there has been an emergence of employing LLM-powered agents as believable human proxies, based on their remarkable decision-making capability. However, existing studies mainly focus on simulating human dialogue…

Collaborative FilteringDecision MakingLanguage ModelingLanguage Modelling+1

Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation

2026-08-05 · Scott H. Hawley hf

Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency. We present a hierarchical self-supervi…