SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens

• URL: http://arxiv.org/abs/2411.19824v2
• Date: Thu, 05 Dec 2024 12:18:04 GMT
• Title: SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
• Authors: Chi Su, Xiaoxuan Ma, Jiajun Su, Yizhou Wang,
• Abstract summary: We propose a one-stage framework for real-time multi-person 3D human mesh estimation from a single RGB image. We introduce scale-adaptive tokens that are dynamically adjusted based on the relative scale of each individual in the image. Experiments show that our method preserves the accuracy benefits of high-resolution processing while substantially reducing computational cost.
• Score: 20.716935111971384
• License:
• Abstract: We propose a one-stage framework for real-time multi-person 3D human mesh estimation from a single RGB image. While current one-stage methods, which follow a DETR-style pipeline, achieve state-of-the-art (SOTA) performance with high-resolution inputs, we observe that this particularly benefits the estimation of individuals in smaller scales of the image (e.g., those far from the camera), but at the cost of significantly increased computation overhead. To address this, we introduce scale-adaptive tokens that are dynamically adjusted based on the relative scale of each individual in the image within the DETR framework. Specifically, individuals in smaller scales are processed at higher resolutions, larger ones at lower resolutions, and background regions are further distilled. These scale-adaptive tokens more efficiently encode the image features, facilitating subsequent decoding to regress the human mesh, while allowing the model to allocate computational resources more effectively and focus on more challenging cases. Experiments show that our method preserves the accuracy benefits of high-resolution processing while substantially reducing computational cost, achieving real-time inference with performance comparable to SOTA methods.

Related papers

• PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [95.98801201266099]
  Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. We propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. Our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR.
  arXiv  Detail & Related papers  (2024-11-26T04:49:42Z)
• Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction [16.082960967820036]
  In this paper, we address the problem of few-shot full 3D head reconstruction. We accomplish this by incorporating a probabilistic shape and appearance prior into coordinate-based representations. We extend the H3DS dataset, which now comprises 60 high-resolution 3D full head scans and their corresponding posed images and masks.
  arXiv  Detail & Related papers  (2023-10-12T07:35:30Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation [65.83008812026635]
  We construct Guided Cost volume Excitation (GCE) and show that simple channel excitation of cost volume guided by image can improve performance considerably. We present an end-to-end network that we call Correlate-and-Excite (CoEx)
  arXiv  Detail & Related papers  (2021-08-12T14:32:26Z)
• FasterPose: A Faster Simple Baseline for Human Pose Estimation [65.8413964785972]
  We propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose. We study the training behavior of FasterPose, and formulate a novel regressive cross-entropy (RCE) loss function for accelerating the convergence. Compared with the previously dominant network of pose estimation, our method reduces 58% of the FLOPs and simultaneously gains 1.3% improvement of accuracy.
  arXiv  Detail & Related papers  (2021-07-07T13:39:08Z)
• Multi-scale Neural ODEs for 3D Medical Image Registration [7.715565365558909]
  Image registration plays an important role in medical image analysis. Deep learning methods such as learn-to-map are much faster but either iterative or coarse-to-fine approach is required to improve accuracy for handling large motions. In this work, we proposed to learn a registration via a multi-scale neural ODE model.
  arXiv  Detail & Related papers  (2021-06-16T00:26:53Z)
• Sample and Computation Redistribution for Efficient Face Detection [137.19388513633484]
  Training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. scrfdf34 outperforms the best competitor, TinaFace, by $3.86%$ (AP at hard set) while being more than emph3$times$ faster on GPUs with VGA-resolution images.
  arXiv  Detail & Related papers  (2021-05-10T23:51:14Z)
• Human Body Model Fitting by Learned Gradient Descent [48.79414884222403]
  We propose a novel algorithm for the fitting of 3D human shape to images. We show that this algorithm is fast (avg. 120ms convergence), robust to dataset, and achieves state-of-the-art results on public evaluation datasets.
  arXiv  Detail & Related papers  (2020-08-19T14:26:47Z)

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.