Pose Priors from Language Models

• URL: http://arxiv.org/abs/2405.03689v1
• Date: Mon, 6 May 2024 17:59:36 GMT
• Title: Pose Priors from Language Models
• Authors: Sanjay Subramanian, Evonne Ng, Lea Müller, Dan Klein, Shiry Ginosar, Trevor Darrell,
• Abstract summary: We present a zero-shot pose optimization method that enforces accurate physical contact constraints. Our method produces surprisingly compelling pose reconstructions of people in close contact. Unlike previous approaches, our method provides a unified framework for resolving self-contact and person-to-person contact.
• Score: 74.61186408764559
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a zero-shot pose optimization method that enforces accurate physical contact constraints when estimating the 3D pose of humans. Our central insight is that since language is often used to describe physical interaction, large pretrained text-based models can act as priors on pose estimation. We can thus leverage this insight to improve pose estimation by converting natural language descriptors, generated by a large multimodal model (LMM), into tractable losses to constrain the 3D pose optimization. Despite its simplicity, our method produces surprisingly compelling pose reconstructions of people in close contact, correctly capturing the semantics of the social and physical interactions. We demonstrate that our method rivals more complex state-of-the-art approaches that require expensive human annotation of contact points and training specialized models. Moreover, unlike previous approaches, our method provides a unified framework for resolving self-contact and person-to-person contact.

Related papers

• 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)
• 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)

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.