DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery

• URL: http://arxiv.org/abs/2411.11214v1
• Date: Mon, 18 Nov 2024 00:46:59 GMT
• Title: DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery
• Authors: Jaewoo Heo, George Hu, Zeyu Wang, Serena Yeung-Levy,
• Abstract summary: DeforHMR is a novel regression-based monocular HMR framework designed to enhance the prediction of human pose parameters. DeforHMR leverages a novel query-agnostic deformable cross-attention mechanism within the transformer decoder. It achieves state-of-the-art performance for single-frame regression-based methods on the widely used 3D HMR benchmarks 3DPW and RICH.
• Score: 2.1653492349540784
• License:
• Abstract: Human Mesh Recovery (HMR) is an important yet challenging problem with applications across various domains including motion capture, augmented reality, and biomechanics. Accurately predicting human pose parameters from a single image remains a challenging 3D computer vision task. In this work, we introduce DeforHMR, a novel regression-based monocular HMR framework designed to enhance the prediction of human pose parameters using deformable attention transformers. DeforHMR leverages a novel query-agnostic deformable cross-attention mechanism within the transformer decoder to effectively regress the visual features extracted from a frozen pretrained vision transformer (ViT) encoder. The proposed deformable cross-attention mechanism allows the model to attend to relevant spatial features more flexibly and in a data-dependent manner. Equipped with a transformer decoder capable of spatially-nuanced attention, DeforHMR achieves state-of-the-art performance for single-frame regression-based methods on the widely used 3D HMR benchmarks 3DPW and RICH. By pushing the boundary on the field of 3D human mesh recovery through deformable attention, we introduce an new, effective paradigm for decoding local spatial information from large pretrained vision encoders in computer vision.

Related papers

• HorGait: A Hybrid Model for Accurate Gait Recognition in LiDAR Point Cloud Planar Projections [8.56443762544299]
  HorGait is a hybrid model with a Transformer architecture for gait recognition on the planar projection of 3D point clouds from LiDAR. It achieves state-of-the-art performance among Transformer architecture methods on the SUSTech1K dataset.
  arXiv  Detail & Related papers  (2024-10-11T02:12:41Z)
• MVSBoost: An Efficient Point Cloud-based 3D Reconstruction [4.282795945742752]
  Efficient and accurate 3D reconstruction is crucial for various applications, including augmented and virtual reality, medical imaging, and cinematic special effects. Traditional Multi-View Stereo (MVS) systems have been fundamental in these applications, but implicit 3D scene modeling has introduced new possibilities for handling complex topologies and continuous surfaces.
  arXiv  Detail & Related papers  (2024-06-19T13:02:17Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• 3D Hand Mesh Recovery from Monocular RGB in Camera Space [3.0453197258042213]
  This study proposes a network model that performs parallel processing of root-relative grids and root recovery tasks. We utilize an implicit learning approach for 2D heatmaps, enhancing the compatibility of 2D cues across different subtasks. Our proposed model is comparable with state-of-the-art models.
  arXiv  Detail & Related papers  (2024-05-12T05:36:37Z)
• SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation [74.07836010698801]
  We propose an SMPL-based Transformer framework (SMPLer) to address this issue. SMPLer incorporates two key ingredients: a decoupled attention operation and an SMPL-based target representation. Extensive experiments demonstrate the effectiveness of SMPLer against existing 3D human shape and pose estimation methods.
  arXiv  Detail & Related papers  (2024-04-23T17:59:59Z)
• Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction [89.53963284958037]
  We propose a novel motion-aware enhancement framework for dynamic scene reconstruction. Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow. For the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed.
  arXiv  Detail & Related papers  (2024-03-18T03:46:26Z)
• W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration [57.37135310143126]
  Previous methods for 3D motion recovery from monocular images often fall short due to reliance on camera coordinates. We introduce W-HMR, a weak-supervised calibration method that predicts "reasonable" focal lengths based on body distortion information. We also present the OrientCorrect module, which corrects body orientation for plausible reconstructions in world space.
  arXiv  Detail & Related papers  (2023-11-29T09:02:07Z)
• Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers [17.22112222736234]
  Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction. Due to the large memory overhead and slow inference speed, it is difficult to deploy such models for practical use. We propose a novel transformer encoder-decoder architecture for 3D human mesh reconstruction from a single image, called FastMETRO.
  arXiv  Detail & Related papers  (2022-07-27T22:54:09Z)
• THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers [67.8628917474705]
  THUNDR is a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people. We show state-of-the-art results on Human3.6M and 3DPW, for both the fully-supervised and the self-supervised models. We observe very solid 3d reconstruction performance for difficult human poses collected in the wild.
  arXiv  Detail & Related papers  (2021-06-17T09:09:24Z)
• PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction [67.08350202974434]
  We propose Parametric Model-Conditioned Implicit Representation (PaMIR), which combines the parametric body model with the free-form deep implicit function. We show that our method achieves state-of-the-art performance for image-based 3D human reconstruction in the cases of challenging poses and clothing types.
  arXiv  Detail & Related papers  (2020-07-08T02:26:19Z)

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.