PyTorchKR Papers

최신 논문

총 423편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.20502

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

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-VAEs). Our model addresses the lack of rich datasets in this domain by incorporating the knowledge and reasoning abilities of LLMs to guide a generative diffusion model. The hierarchical VQ-VAE architecture captures different motion-specific characteristics at multiple levels of abstraction, avoiding redundant concepts and enabling efficient multi-resolution representation. We introduce a diffusion model that operates in the latent space and incorporates LLM-generated motion planning cues to guide the denoising process, resulting in prompt-specific motion generation with greater control and diversity. Experimental results on the CORE-4D, and InterHuman datasets demonstrate the effectiveness of our approach in generating realistic and diverse collaborative human-object-human interactions, outperforming state-of-the-art methods. Our work opens up new possibilities for modeling complex interactions in various domains, such as robotics, graphics and computer vision.

arXiv:2409.17686

MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling

Motion generation from discrete quantization offers many advantages over continuous regression, but at the cost of inevitable approximation errors. Previous methods usually quantize the entire body pose into one code, which not only faces the difficulty in encoding all joints within one vector but also loses the spatial relationship between different joints. Differently, in this work we quantize each individual joint into one vector, which i) simplifies the quantization process as the complexity associated with a single joint is markedly lower than that of the entire pose; ii) maintains a spatial-temporal structure that preserves both the spatial relationships among joints and the temporal movement patterns; iii) yields a 2D token map, which enables the application of various 2D operations widely used in 2D images. Grounded in the 2D motion quantization, we build a spatial-temporal modeling framework, where 2D joint VQVAE, temporal-spatial 2D masking technique, and spatial-temporal 2D attention are proposed to take advantage of spatial-temporal signals among the 2D tokens. Extensive experiments demonstrate that our method significantly outperforms previous methods across different datasets, with a 26.6% decrease of FID on HumanML3D and a 29.9% decrease on KIT-ML. Project page: https://aigc3d.github.io/mogents.

arXiv:2409.18127

EgoLM: Multi-Modal Language Model of Egocentric Motions

As the prevalence of wearable devices, learning egocentric motions becomes essential to develop contextual AI. In this work, we present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs, e.g., egocentric videos and motion sensors. EgoLM exploits rich contexts for the disambiguation of egomotion tracking and understanding, which are ill-posed under single modality conditions. To facilitate the versatile and multi-modal framework, our key insight is to model the joint distribution of egocentric motions and natural languages using large language models (LLM). Multi-modal sensor inputs are encoded and projected to the joint latent space of language models, and used to prompt motion generation or text generation for egomotion tracking or understanding, respectively. Extensive experiments on large-scale multi-modal human motion dataset validate the effectiveness of EgoLM as a generalist model for universal egocentric learning.

arXiv:2409.13426

HMD$^2$: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device

This paper investigates the online generation of realistic full-body human motion using a single head-mounted device with an outward-facing color camera and the ability to perform visual SLAM. Given the inherent ambiguity of this setup, we introduce a novel system, HMD$^2$, designed to balance between motion reconstruction and generation. From a reconstruction standpoint, our system aims to maximally utilize the camera streams to produce both analytical and learned features, including head motion, SLAM point cloud, and image embeddings. On the generative front, HMD$^2$ employs a multi-modal conditional motion Diffusion model, incorporating a time-series backbone to maintain temporal coherence in generated motions, and utilizes autoregressive in-painting to facilitate online motion inference with minimal latency (0.17 seconds). Collectively, we demonstrate that our system offers a highly effective and robust solution capable of scaling to an extensive dataset of over 200 hours collected in a wide range of complex indoor and outdoor environments using publicly available smart glasses.

arXiv:2409.13998

Relevance-driven Decision Making for Safer and More Efficient Human Robot Collaboration

Human brain possesses the ability to effectively focus on important environmental components, which enhances perception, learning, reasoning, and decision-making. Inspired by this cognitive mechanism, we introduced a novel concept termed relevance for Human-Robot Collaboration (HRC). Relevance is a dimensionality reduction process that incorporates a continuously operating perception module, evaluates cue sufficiency within the scene, and applies a flexible formulation and computation framework. In this paper, we present an enhanced two-loop framework that integrates real-time and asynchronous processing to quantify relevance and leverage it for safer and more efficient human-robot collaboration (HRC). The two-loop framework integrates an asynchronous loop, which leverages LLM world knowledge to quantify relevance, and a real-time loop, which performs scene understanding, human intent prediction, and decision-making based on relevance. HRC decision-making is enhanced by a relevance-based task allocation method, as well as a motion generation and collision avoidance approach that incorporates human trajectory prediction. Simulations and experiments show that our methodology for relevance quantification can accurately and robustly predict the human objective and relevance, with an average accuracy of up to 0.90 for objective prediction and up to 0.96 for relevance prediction. Moreover, our motion generation methodology reduces collision cases by 63.76% and collision frames by 44.74% when compared with a state-of-the-art (SOTA) collision avoidance method. Our framework and methodologies, with relevance, guide the robot on how to best assist humans and generate safer and more efficient actions for HRC.

arXiv:2409.12140공식 코드 · Papers with Code

MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion retrieval process. By effectively prompting large language models (LLMs), we address spelling errors and rephrasing issues in motion retrieval. Our approach utilizes a multi-part retrieval strategy to improve the generalizability of motion retrieval across the language space. We create diverse samples through the spatial composition of the retrieved motions. Furthermore, by utilizing low-level, part-specific motion information, we can construct motion samples for unseen text descriptions. Our experiments demonstrate that our framework can serve as a plug-and-play module, improving the performance of motion diffusion models. Code, pretrained models and sample videos are available at: https://motion-rag.github.io/

arXiv:2409.11676

Hypergraph-based Motion Generation with Multi-modal Interaction Relational Reasoning

The intricate nature of real-world driving environments, characterized by dynamic and diverse interactions among multiple vehicles and their possible future states, presents considerable challenges in accurately predicting the motion states of vehicles and handling the uncertainty inherent in the predictions. Addressing these challenges requires comprehensive modeling and reasoning to capture the implicit relations among vehicles and the corresponding diverse behaviors. This research introduces an integrated framework for autonomous vehicles (AVs) motion prediction to address these complexities, utilizing a novel Relational Hypergraph Interaction-informed Neural mOtion generator (RHINO). RHINO leverages hypergraph-based relational reasoning by integrating a multi-scale hypergraph neural network to model group-wise interactions among multiple vehicles and their multi-modal driving behaviors, thereby enhancing motion prediction accuracy and reliability. Experimental validation using real-world datasets demonstrates the superior performance of this framework in improving predictive accuracy and fostering socially aware automated driving in dynamic traffic scenarios.

arXiv:2409.10847공식 코드 · Papers with Code

BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation

Autoregressive models excel in modeling sequential dependencies by enforcing causal constraints, yet they struggle to capture complex bidirectional patterns due to their unidirectional nature. In contrast, mask-based models leverage bidirectional context, enabling richer dependency modeling. However, they often assume token independence during prediction, which undermines the modeling of sequential dependencies. Additionally, the corruption of sequences through masking or absorption can introduce unnatural distortions, complicating the learning process. To address these issues, we propose Bidirectional Autoregressive Diffusion (BAD), a novel approach that unifies the strengths of autoregressive and mask-based generative models. BAD utilizes a permutation-based corruption technique that preserves the natural sequence structure while enforcing causal dependencies through randomized ordering, enabling the effective capture of both sequential and bidirectional relationships. Comprehensive experiments show that BAD outperforms autoregressive and mask-based models in text-to-motion generation, suggesting a novel pre-training strategy for sequence modeling. The codebase for BAD is available on https://github.com/RohollahHS/BAD.

arXiv:2409.10308

Know your limits! Optimize the robot's behavior through self-awareness

As humanoid robots transition from labs to real-world environments, it is essential to democratize robot control for non-expert users. Recent human-robot imitation algorithms focus on following a reference human motion with high precision, but they are susceptible to the quality of the reference motion and require the human operator to simplify its movements to match the robot's capabilities. Instead, we consider that the robot should understand and adapt the reference motion to its own abilities, facilitating the operator's task. For that, we introduce a deep-learning model that anticipates the robot's performance when imitating a given reference. Then, our system can generate multiple references given a high-level task command, assign a score to each of them, and select the best reference to achieve the desired robot behavior. Our Self-AWare model (SAW) ranks potential robot behaviors based on various criteria, such as fall likelihood, adherence to the reference motion, and smoothness. We integrate advanced motion generation, robot control, and SAW in one unique system, ensuring optimal robot behavior for any task command. For instance, SAW can anticipate falls with 99.29% accuracy. For more information check our project page: https://evm7.github.io/Self-AWare

arXiv:2409.08857

InstantDrag: Improving Interactivity in Drag-based Image Editing

Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

arXiv:2409.06791

Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening

Human motion generation is an important area of research in many fields. In this work, we tackle the problem of motion stitching and in-betweening. Current methods either require manual efforts, or are incapable of handling longer sequences. To address these challenges, we propose a diffusion model with a transformer-based denoiser to generate realistic human motion. Our method demonstrated strong performance in generating in-betweening sequences, transforming a variable number of input poses into smooth and realistic motion sequences consisting of 75 frames at 15 fps, resulting in a total duration of 5 seconds. We present the performance evaluation of our method using quantitative metrics such as Frechet Inception Distance (FID), Diversity, and Multimodality, along with visual assessments of the generated outputs.

arXiv:2409.01591

Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformers

Our research presents a novel motion generation framework designed to produce whole-body motion sequences conditioned on multiple modalities simultaneously, specifically text and audio inputs. Leveraging Vector Quantized Variational Autoencoders (VQVAEs) for motion discretization and a bidirectional Masked Language Modeling (MLM) strategy for efficient token prediction, our approach achieves improved processing efficiency and coherence in the generated motions. By integrating spatial attention mechanisms and a token critic we ensure consistency and naturalness in the generated motions. This framework expands the possibilities of motion generation, addressing the limitations of existing approaches and opening avenues for multimodal motion synthesis.

arXiv:2409.01522

Lagrangian Motion Fields for Long-term Motion Generation

Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise motion representations, which capture only static spatial details and overlook temporal dynamics. This approach leads to significant redundancy across the temporal dimension, complicating the generation of effective long-term motion. To overcome these limitations, we introduce the novel concept of Lagrangian Motion Fields, specifically designed for long-term motion generation. By treating each joint as a Lagrangian particle with uniform velocity over short intervals, our approach condenses motion representations into a series of "supermotions" (analogous to superpixels). This method seamlessly integrates static spatial information with interpretable temporal dynamics, transcending the limitations of existing network architectures and motion sequence content types. Our solution is versatile and lightweight, eliminating the need for neural network preprocessing. Our approach excels in tasks such as long-term music-to-dance generation and text-to-motion generation, offering enhanced efficiency, superior generation quality, and greater diversity compared to existing methods. Additionally, the adaptability of Lagrangian Motion Fields extends to applications like infinite motion looping and fine-grained controlled motion generation, highlighting its broad utility. Video demonstrations are available at \url{https://plyfager.github.io/LaMoG}.

arXiv:2408.17135

TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation

Human-human motion generation is essential for understanding humans as social beings. Current methods fall into two main categories: single-person-based methods and separate modeling-based methods. To delve into this field, we abstract the overall generation process into a general framework MetaMotion, which consists of two phases: temporal modeling and interaction mixing. For temporal modeling, the single-person-based methods concatenate two people into a single one directly, while the separate modeling-based methods skip the modeling of interaction sequences. The inadequate modeling described above resulted in sub-optimal performance and redundant model parameters. In this paper, we introduce TIMotion (Temporal and Interactive Modeling), an efficient and effective framework for human-human motion generation. Specifically, we first propose Causal Interactive Injection to model two separate sequences as a causal sequence leveraging the temporal and causal properties. Then we present Role-Evolving Scanning to adjust to the change in the active and passive roles throughout the interaction. Finally, to generate smoother and more rational motion, we design Localized Pattern Amplification to capture short-term motion patterns. Extensive experiments on InterHuman and InterX demonstrate that our method achieves superior performance. Project page: https://aigc-explorer.github.io/TIMotion-page/

arXiv:2408.12885공식 코드 · Papers with Code

T3M: Text Guided 3D Human Motion Synthesis from Speech

Speech-driven 3D motion synthesis seeks to create lifelike animations based on human speech, with potential uses in virtual reality, gaming, and the film production. Existing approaches reply solely on speech audio for motion generation, leading to inaccurate and inflexible synthesis results. To mitigate this problem, we introduce a novel text-guided 3D human motion synthesis method, termed \textit{T3M}. Unlike traditional approaches, T3M allows precise control over motion synthesis via textual input, enhancing the degree of diversity and user customization. The experiment results demonstrate that T3M can greatly outperform the state-of-the-art methods in both quantitative metrics and qualitative evaluations. We have publicly released our code at \href{https://github.com/Gloria2tt/T3M.git}{https://github.com/Gloria2tt/T3M.git}

arXiv:2408.13239공식 코드 · Papers with Code

CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of video diffusion models (VDMs) to combine concepts and generate motions. To restore these abilities, some methods use additional video similar to the prompt to fine-tune or guide the model. This requires frequent changes of guiding videos and even re-tuning of the model when generating different motions, which is very inconvenient for users. In this paper, we propose CustomCrafter, a novel framework that preserves the model's motion generation and conceptual combination abilities without additional video and fine-tuning to recovery. For preserving conceptual combination ability, we design a plug-and-play module to update few parameters in VDMs, enhancing the model's ability to capture the appearance details and the ability of concept combinations for new subjects. For motion generation, we observed that VDMs tend to restore the motion of video in the early stage of denoising, while focusing on the recovery of subject details in the later stage. Therefore, we propose Dynamic Weighted Video Sampling Strategy. Using the pluggability of our subject learning modules, we reduce the impact of this module on motion generation in the early stage of denoising, preserving the ability to generate motion of VDMs. In the later stage of denoising, we restore this module to repair the appearance details of the specified subject, thereby ensuring the fidelity of the subject's appearance. Experimental results show that our method has a significant improvement compared to previous methods. Code is available at https://github.com/WuTao-CS/CustomCrafter

arXiv:2408.09397

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the multiple-input-multiple-output (MIMO) nature of the generative model of interest. More concretely, on the input end, the model typically consumes both speech signals and character guidance (e.g., identity and emotion), which not only poses challenge on learning capacity but also hinders further adaptation to varying guidance; on the output end, holistic human motions mainly consist of facial expressions and body movements, which are inherently correlated but non-trivial to coordinate in current data-driven generation process. In response to the above challenge, we propose tailored designs to both ends. For the former, we propose to pre-train on data regarding a fixed identity with neutral emotion, and defer the incorporation of customizable conditions (identity and emotion) to fine-tuning stage, which is boosted by our novel X-Adapter for parameter-efficient fine-tuning. For the latter, we propose a simple yet effective transformer design, DU-Trans, which first divides into two branches to learn individual features of face expression and body movements, and then unites those to learn a joint bi-directional distribution and directly predicts combined coefficients. Evaluated on BEAT2 and SHOW datasets, Combo is highly effective in generating high-quality motions but also efficient in transferring identity and emotion. Project website: \href{https://xc-csc101.github.io/combo/}{Combo}.

arXiv:2408.06614

ViMo: Generating Motions from Casual Videos

Although humans have the innate ability to imagine multiple possible actions from videos, it remains an extraordinary challenge for computers due to the intricate camera movements and montages. Most existing motion generation methods predominantly rely on manually collected motion datasets, usually tediously sourced from motion capture (Mocap) systems or Multi-View cameras, unavoidably resulting in a limited size that severely undermines their generalizability. Inspired by recent advance of diffusion models, we probe a simple and effective way to capture motions from videos and propose a novel Video-to-Motion-Generation framework (ViMo) which could leverage the immense trove of untapped video content to produce abundant and diverse 3D human motions. Distinct from prior work, our videos could be more causal, including complicated camera movements and occlusions. Striking experimental results demonstrate the proposed model could generate natural motions even for videos where rapid movements, varying perspectives, or frequent occlusions might exist. We also show this work could enable three important downstream applications, such as generating dancing motions according to arbitrary music and source video style. Extensive experimental results prove that our model offers an effective and scalable way to generate diversity and realistic motions. Code and demos will be public soon.

arXiv:2408.00712

MotionFix: Text-Driven 3D Human Motion Editing

The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. In this paper, we address both challenges. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text, introducing the new MotionFix dataset. Access to this data allows us to train a conditional diffusion model, TMED, that takes both the source motion and the edit text as input. We develop several baselines to evaluate our model, comparing it against models trained solely on text-motion pair datasets, and demonstrate the superior performance of our model trained on triplets. We also introduce new retrieval-based metrics for motion editing, establishing a benchmark on the evaluation set of MotionFix. Our results are promising, paving the way for further research in fine-grained motion generation. Code, models, and data are available at https://motionfix.is.tue.mpg.de/ .

arXiv:2408.00352

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Human motion generation driven by deep generative models has enabled compelling applications, but the ability of text-to-motion (T2M) models to produce realistic motions from text prompts raises security concerns if exploited maliciously. Despite growing interest in T2M, few methods focus on safeguarding these models against adversarial attacks, with existing work on text-to-image models proving insufficient for the unique motion domain. In the paper, we propose ALERT-Motion, an autonomous framework leveraging large language models (LLMs) to craft targeted adversarial attacks against black-box T2M models. Unlike prior methods modifying prompts through predefined rules, ALERT-Motion uses LLMs' knowledge of human motion to autonomously generate subtle yet powerful adversarial text descriptions. It comprises two key modules: an adaptive dispatching module that constructs an LLM-based agent to iteratively refine and search for adversarial prompts; and a multimodal information contrastive module that extracts semantically relevant motion information to guide the agent's search. Through this LLM-driven approach, ALERT-Motion crafts adversarial prompts querying victim models to produce outputs closely matching targeted motions, while avoiding obvious perturbations. Evaluations across popular T2M models demonstrate ALERT-Motion's superiority over previous methods, achieving higher attack success rates with stealthier adversarial prompts. This pioneering work on T2M adversarial attacks highlights the urgency of developing defensive measures as motion generation technology advances, urging further research into safe and responsible deployment.