Pose Priors from Language Models

• URL: http://arxiv.org/abs/2405.03689v2
• Date: Thu, 15 May 2025 14:35:43 GMT
• Title: Pose Priors from Language Models
• Authors: Sanjay Subramanian, Evonne Ng, Lea Müller, Dan Klein, Shiry Ginosar, Trevor Darrell,
• Abstract summary: Language is often used to describe physical interaction, yet most 3D human pose estimation methods overlook this rich source of information.<n>We bridge this gap by leveraging large multimodal models (LMMs) as priors for reconstructing contact poses.
• Score: 74.61186408764559
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language is often used to describe physical interaction, yet most 3D human pose estimation methods overlook this rich source of information. We bridge this gap by leveraging large multimodal models (LMMs) as priors for reconstructing contact poses, offering a scalable alternative to traditional methods that rely on human annotations or motion capture data. Our approach extracts contact-relevant descriptors from an LMM and translates them into tractable losses to constrain 3D human pose optimization. Despite its simplicity, our method produces compelling reconstructions for both two-person interactions and self-contact scenarios, accurately capturing the semantics of physical and social interactions. Our results demonstrate that LMMs can serve as powerful tools for contact prediction and pose estimation, offering an alternative to costly manual human annotations or motion capture data. Our code is publicly available at https://prosepose.github.io.

Related papers

• Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning [50.76723760768117]
  Existing human pose estimation methods cannot recover plausible close interactions from in-the-wild videos.<n>We find that human appearance can provide a straightforward cue to address these obstacles.<n>We propose a dual-branch optimization framework to reconstruct accurate interactive motions with plausible body contacts constrained by human appearances, social proxemics, and physical laws.
  arXiv  Detail & Related papers  (2025-07-03T12:19:26Z)
• InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing [36.29681929804816]
  We propose a novel zero-shot 3D HOI generation framework without training on specific datasets.<n>We use a pre-trained 2D image diffusion model to parse unseen objects and extract contact points.<n>We then introduce a detailed optimization to generate fine-grained, precise, and natural interaction, enforcing realistic 3D contact between the 3D object and the involved body parts.
  arXiv  Detail & Related papers  (2025-05-30T07:53:55Z)
• A Guide to Structureless Visual Localization [63.41481414949785]
  Methods that estimate the camera pose of a query image in a known scene are core components of many applications, including self-driving cars and augmented / mixed reality systems. State-of-the-art visual localization algorithms are structure-based, i.e., they store a 3D model of the scene and use 2D-3D correspondences between the query image and 3D points in the model for camera pose estimation. This paper is dedicated to providing, to the best of our knowledge, first comprehensive discussion and comparison of structureless methods.
  arXiv  Detail & Related papers  (2025-04-24T15:08:36Z)
• Adapting Human Mesh Recovery with Vision-Language Feedback [17.253535686451897]
  We leverage vision-language models to generate interactive body part descriptions.<n>We train a text encoder and a pose VQ-VAE, aligning texts to body poses in a shared latent space.<n>The model can produce poses with accurate 3D perception and image consistency.
  arXiv  Detail & Related papers  (2025-02-06T07:42:00Z)
• SPARK: Self-supervised Personalized Real-time Monocular Face Capture [6.093606972415841]
  Current state of the art approaches have the ability to regress parametric 3D face models in real-time across a wide range of identities. We propose a method for high-precision 3D face capture taking advantage of a collection of unconstrained videos of a subject as prior information.
  arXiv  Detail & Related papers  (2024-09-12T12:30:04Z)
• StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset [56.71580976007712]
  We propose to use the Human-Object Offset between anchors which are densely sampled from the surface of human mesh and object mesh to represent human-object spatial relation. Based on this representation, we propose Stacked Normalizing Flow (StackFLOW) to infer the posterior distribution of human-object spatial relations from the image. During the optimization stage, we finetune the human body pose and object 6D pose by maximizing the likelihood of samples.
  arXiv  Detail & Related papers  (2024-07-30T04:57:21Z)
• Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption [64.07607726562841]
  Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration. In this work, we tackle the task of reconstructing closely interactive humans from a monocular video. We propose to leverage knowledge from proxemic behavior and physics to compensate the lack of visual information.
  arXiv  Detail & Related papers  (2024-04-17T11:55:45Z)
• Social-Transmotion: Promptable Human Trajectory Prediction [65.80068316170613]
  Social-Transmotion is a generic Transformer-based model that exploits diverse and numerous visual cues to predict human behavior.<n>Our approach is validated on multiple datasets, including JTA, JRDB, Pedestrians and Cyclists in Road Traffic, and ETH-UCY.
  arXiv  Detail & Related papers  (2023-12-26T18:56:49Z)
• Generative Proxemics: A Prior for 3D Social Interaction from Images [32.547187575678464]
  Social interaction is a fundamental aspect of human behavior and communication. We present a novel approach that learns a prior over the 3D proxemics two people in close social interaction. Our approach recovers accurate and plausible 3D social interactions from noisy initial estimates, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-15T17:59:20Z)
• Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors [42.17542596399014]
  We present a method for inferring diverse 3D models of human-object interactions from images. Our method extracts high-level commonsense knowledge from large language models. We quantitatively evaluate the inferred 3D models on a large human-object interaction dataset.
  arXiv  Detail & Related papers  (2022-09-06T13:32:55Z)
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies [78.17425779503047]
  We propose a novel neural implicit representation for the human body. It is fully differentiable and optimizable with disentangled shape and pose latent spaces. Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
  arXiv  Detail & Related papers  (2021-11-30T04:10:57Z)
• Contact-Aware Retargeting of Skinned Motion [49.71236739408685]
  This paper introduces a motion estimation method that preserves self-contacts and prevents interpenetration. The method identifies self-contacts and ground contacts in the input motion, and optimize the motion to apply to the output skeleton. In experiments, our results quantitatively outperform previous methods and we conduct a user study where our retargeted motions are rated as higher-quality than those produced by recent works.
  arXiv  Detail & Related papers  (2021-09-15T17:05:02Z)
• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration [67.69257782645789]
  We propose piecewise transformation fields that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We show that fitting parametric models with poses by our network results in much better registration quality, especially for extreme poses.
  arXiv  Detail & Related papers  (2021-04-16T15:16:09Z)
• Monocular Real-time Full Body Capture with Inter-part Correlations [66.22835689189237]
  We present the first method for real-time full body capture that estimates shape and motion of body and hands together with a dynamic 3D face model from a single color image. Our approach uses a new neural network architecture that exploits correlations between body and hands at high computational efficiency.
  arXiv  Detail & Related papers  (2020-12-11T02:37:56Z)
• HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation [54.23770284299979]
  This paper introduces a novel form of supervision - Hierarchical Multi-person Ordinal Relations (HMOR) HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically. An integrated top-down model is designed to leverage these ordinal relations in the learning process. The proposed method significantly outperforms state-of-the-art methods on publicly available multi-person 3D pose datasets.
  arXiv  Detail & Related papers  (2020-08-01T07:53:27Z)
• Cascaded deep monocular 3D human pose estimation with evolutionary training data [76.3478675752847]
  Deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation. This paper proposes a novel data augmentation method that is scalable for massive amount of training data. Our method synthesizes unseen 3D human skeletons based on a hierarchical human representation and synthesizings inspired by prior knowledge.
  arXiv  Detail & Related papers  (2020-06-14T03:09:52Z)

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.