STMR: Spiral Transformer for Hand Mesh Reconstruction

• URL: http://arxiv.org/abs/2407.05967v1
• Date: Mon, 8 Jul 2024 14:05:27 GMT
• Title: STMR: Spiral Transformer for Hand Mesh Reconstruction
• Authors: Huilong Xie, Wenwei Song, Wenxiong Kang, Yihong Lin,
• Abstract summary: This paper ingeniously integrates spiral sampling into the Transformer architecture, enhancing its ability to leverage mesh topology for superior performance in hand mesh reconstruction. Experiments on the FreiHAND dataset demonstrate the state-of-the-art performance and unparalleled inference speed of STMR compared with similar backbone methods.
• Score: 11.47314655711821
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in both transformer-based methods and spiral neighbor sampling techniques have greatly enhanced hand mesh reconstruction. Transformers excel in capturing complex vertex relationships, and spiral neighbor sampling is vital for utilizing topological structures. This paper ingeniously integrates spiral sampling into the Transformer architecture, enhancing its ability to leverage mesh topology for superior performance in hand mesh reconstruction, resulting in substantial accuracy boosts. STMR employs a single image encoder for model efficiency. To augment its information extraction capability, we design the multi-scale pose feature extraction (MSPFE) module, which facilitates the extraction of rich pose features, ultimately enhancing the model's performance. Moreover, the proposed predefined pose-to-vertex lifting (PPVL) method improves vertex feature representation, further boosting reconstruction performance. Extensive experiments on the FreiHAND dataset demonstrate the state-of-the-art performance and unparalleled inference speed of STMR compared with similar backbone methods, showcasing its efficiency and effectiveness. The code is available at https://github.com/SmallXieGithub/STMR.

Related papers

• Efficient Visual State Space Model for Image Deblurring [83.57239834238035]
  Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration. We propose a simple yet effective visual state space model (EVSSM) for image deblurring.
  arXiv  Detail & Related papers  (2024-05-23T09:13:36Z)
• CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection [1.837431956557716]
  Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection. We propose a novel decoder block that integrates feature pyramids and transformers. Our model achieves superior performance in detecting small objects compared to existing methods.
  arXiv  Detail & Related papers  (2024-04-23T18:46:07Z)
• DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model [18.25548360119976]
  This paper endeavors to advance the precision of snapshot compressive imaging (SCI) reconstruction for multispectral image (MSI) We propose a novel structured zero-shot diffusion model, dubbed DiffSCI. We present extensive testing to show that DiffSCI exhibits discernible performance enhancements over prevailing self-supervised and zero-shot approaches.
  arXiv  Detail & Related papers  (2023-11-19T20:27:14Z)
• Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection [77.50110439560152]
  Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) We propose a novel and efficient context modeling mechanism that can help existing FPs deliver better MFF results. In particular, we introduce a novel insight that comprehensive contexts can be decomposed and condensed into two types of representations for higher efficiency.
  arXiv  Detail & Related papers  (2022-07-14T01:45:03Z)
• ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer [60.27951773998535]
  We propose a recurrent transformer model, namely textbfReconFormer, for MRI reconstruction. It can iteratively reconstruct high fertility magnetic resonance images from highly under-sampled k-space data. We show that it achieves significant improvements over the state-of-the-art methods with better parameter efficiency.
  arXiv  Detail & Related papers  (2022-01-23T21:58:19Z)
• Spectral Compressive Imaging Reconstruction Using Convolution and Contextual Transformer [6.929652454131988]
  We propose a hybrid network module, namely CCoT (Contextual Transformer) block, which can acquire the inductive bias ability of transformer simultaneously. We integrate the proposed CCoT block into deep unfolding framework based on the generalized alternating projection algorithm, and further propose the GAP-CT network.
  arXiv  Detail & Related papers  (2022-01-15T06:30:03Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Transformer Assisted Convolutional Network for Cell Instance Segmentation [5.195101477698897]
  We present a transformer based approach to enhance the performance of the conventional convolutional feature extractor. Our approach merges the convolutional feature maps with transformer-based token embeddings by applying a projection operation similar to self-attention in transformers.
  arXiv  Detail & Related papers  (2021-10-05T18:18:31Z)
• Fourier Space Losses for Efficient Perceptual Image Super-Resolution [131.50099891772598]
  We show that it is possible to improve the performance of a recently introduced efficient generator architecture solely with the application of our proposed loss functions. We show that our losses' direct emphasis on the frequencies in Fourier-space significantly boosts the perceptual image quality. The trained generator achieves comparable results with and is 2.4x and 48x faster than state-of-the-art perceptual SR methods RankSRGAN and SRFlow respectively.
  arXiv  Detail & Related papers  (2021-06-01T20:34:52Z)
• Kullback-Leibler Divergence-Based Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation [152.609322951917]
  We come up with a Kullback-Leibler (KL) divergence-based Fuzzy C-Means (FCM) algorithm by incorporating a tight wavelet frame transform and a morphological reconstruction operation. The proposed algorithm works well and comes with better segmentation performance than other comparative algorithms.
  arXiv  Detail & Related papers  (2020-02-21T05:19:10Z)

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.