VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions

• URL: http://arxiv.org/abs/2506.23236v1
• Date: Sun, 29 Jun 2025 13:48:38 GMT
• Title: VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions
• Authors: Marko Mihajlovic, Siwei Zhang, Gen Li, Kaifeng Zhao, Lea Müller, Siyu Tang,
• Abstract summary: Parametric human body models play a crucial role in computer graphics and vision, enabling applications ranging from human motion analysis to understanding human-environment interactions.<n>To address this limitation, recent research has explored volumetric neural implicit body models.<n>We introduce VolumetricSMPL, a neural body model that generates compact, yet efficient decoders.
• Score: 17.542908770824596
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parametric human body models play a crucial role in computer graphics and vision, enabling applications ranging from human motion analysis to understanding human-environment interactions. Traditionally, these models use surface meshes, which pose challenges in efficiently handling interactions with other geometric entities, such as objects and scenes, typically represented as meshes or point clouds. To address this limitation, recent research has explored volumetric neural implicit body models. However, existing works are either insufficiently robust for complex human articulations or impose high computational and memory costs, limiting their widespread use. To this end, we introduce VolumetricSMPL, a neural volumetric body model that leverages Neural Blend Weights (NBW) to generate compact, yet efficient MLP decoders. Unlike prior approaches that rely on large MLPs, NBW dynamically blends a small set of learned weight matrices using predicted shape- and pose-dependent coefficients, significantly improving computational efficiency while preserving expressiveness. VolumetricSMPL outperforms prior volumetric occupancy model COAP with 10x faster inference, 6x lower GPU memory usage, enhanced accuracy, and a Signed Distance Function (SDF) for efficient and differentiable contact modeling. We demonstrate VolumetricSMPL's strengths across four challenging tasks: (1) reconstructing human-object interactions from in-the-wild images, (2) recovering human meshes in 3D scenes from egocentric views, (3) scene-constrained motion synthesis, and (4) resolving self-intersections. Our results highlight its broad applicability and significant performance and efficiency gains.

Related papers

• 3HANDS Dataset: Learning from Humans for Generating Naturalistic Handovers with Supernumerary Robotic Limbs [64.99122701615151]
  Supernumerary robotic limbs (SRLs) are robotic structures integrated closely with the user's body.<n>We present 3HANDS, a novel dataset of object handover interactions between a participant performing a daily activity and another participant enacting a hip-mounted SRL in a naturalistic manner.<n>We present three models that generate naturalistic handover trajectories, one that determines the appropriate handover endpoints, and a third that predicts the moment to initiate a handover.
  arXiv  Detail & Related papers  (2025-03-06T17:23:55Z)
• NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation [24.059039655555807]
  3D human pose estimation (HPE) is limited by resource-constrained edge devices.<n>We propose a Nano Human Topology Network (NanoHTNet) to capture explicit features.<n>We also propose PoseCLR to align 2D poses from diverse viewpoints in a proxy task.
  arXiv  Detail & Related papers  (2025-01-27T04:16:42Z)
• LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models [35.01842161084472]
  We propose a new physical reasoning task and a dataset, dubbed TraySim.<n>Our task involves predicting the dynamics of several objects on a tray that is given an external impact.<n>We present LLMPhy, a zero-shot black-box optimization framework that leverages the physics knowledge and program synthesis abilities of LLMs.<n>Our results show that the combination of the LLM and the physics engine leads to state-of-the-art zero-shot physical reasoning performance.
  arXiv  Detail & Related papers  (2024-11-12T18:56:58Z)
• EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting [95.44545809256473]
  EgoGaussian is a method capable of simultaneously reconstructing 3D scenes and dynamically tracking 3D object motion from RGB egocentric input alone. We show significant improvements in terms of both dynamic object and background reconstruction quality compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-06-28T10:39:36Z)
• Scaling Up Dynamic Human-Scene Interaction Modeling [58.032368564071895]
  TRUMANS is the most comprehensive motion-captured HSI dataset currently available. It intricately captures whole-body human motions and part-level object dynamics. We devise a diffusion-based autoregressive model that efficiently generates HSI sequences of any length.
  arXiv  Detail & Related papers  (2024-03-13T15:45:04Z)
• Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions [82.90906153293585]
  We propose a graph neural network, HO-GCN, to fuse motion data and dynamic descriptors for the prediction task. We show the proposed network that consumes dynamic descriptors can achieve state-of-the-art prediction results and help the network better generalize to unseen objects.
  arXiv  Detail & Related papers  (2022-06-25T09:55:39Z)
• NeuralFusion: Neural Volumetric Rendering under Human-object Interactions [46.70371238621842]
  We propose a neural approach for volumetric human-object capture and rendering using sparse consumer RGBD sensors. For geometry modeling, we propose a neural implicit inference scheme with non-rigid key-volume fusion. We also introduce a layer-wise human-object texture rendering scheme, which combines volumetric and image-based rendering in both spatial and temporal domains.
  arXiv  Detail & Related papers  (2022-02-25T17:10:07Z)
• 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)
• RobustFusion: Robust Volumetric Performance Reconstruction under Human-object Interactions from Monocular RGBD Stream [27.600873320989276]
  High-quality 4D reconstruction of human performance with complex interactions to various objects is essential in real-world scenarios. Recent advances still fail to provide reliable performance reconstruction. We propose RobustFusion, a robust volumetric performance reconstruction system for human-object interaction scenarios.
  arXiv  Detail & Related papers  (2021-04-30T08:41:45Z)

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.