STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution

• URL: http://arxiv.org/abs/2506.16061v1
• Date: Thu, 19 Jun 2025 06:38:49 GMT
• Title: STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution
• Authors: Yucheng Jin, Jinyan Chen, Ziyue He, Baojun Han, Furan An,
• Abstract summary: We propose a spatial-temporal adaptive super-resolution framework specifically designed for video-based human pose estimation.<n>Our method features a novel spatial-temporal Transformer with LeakyReLU-modified linear attention, which efficiently captures long-range temporal dependencies.<n>It achieves up to 5.2% mAP improvement under extremely low-resolution (64x48) conditions while delivering 2.8x to 4.4x faster inference than cascaded approaches.
• Score: 2.3324945410076685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human pose estimation in low-resolution videos presents a fundamental challenge in computer vision. Conventional methods either assume high-quality inputs or employ computationally expensive cascaded processing, which limits their deployment in resource-constrained environments. We propose STAR-Pose, a spatial-temporal adaptive super-resolution framework specifically designed for video-based human pose estimation. Our method features a novel spatial-temporal Transformer with LeakyReLU-modified linear attention, which efficiently captures long-range temporal dependencies. Moreover, it is complemented by an adaptive fusion module that integrates parallel CNN branch for local texture enhancement. We also design a pose-aware compound loss to achieve task-oriented super-resolution. This loss guides the network to reconstruct structural features that are most beneficial for keypoint localization, rather than optimizing purely for visual quality. Extensive experiments on several mainstream video HPE datasets demonstrate that STAR-Pose outperforms existing approaches. It achieves up to 5.2% mAP improvement under extremely low-resolution (64x48) conditions while delivering 2.8x to 4.4x faster inference than cascaded approaches.

Related papers

• SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution [55.14432034345353]
  We study key design principles for latter cascaded video super-resolution models, which are underexplored currently.<n>First, we propose two strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator.<n>Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs.
  arXiv  Detail & Related papers  (2025-06-24T17:57:26Z)
• Super-Resolution for Remote Sensing Imagery via the Coupling of a Variational Model and Deep Learning [20.697932997351813]
  gradient-guided multi-frame super-resolution (MFSR) framework for remote sensing imagery reconstruction.<n>We propose a novel gradient-guided multi-frame super-resolution (MFSR) framework for remote sensing imagery reconstruction.
  arXiv  Detail & Related papers  (2024-12-13T04:19:48Z)
• VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models [58.464465016269614]
  We propose a novel framework for solving high-definition video inverse problems using latent image diffusion models.<n>Our approach delivers HD-resolution reconstructions in under 6 seconds per frame on a single NVIDIA 4090 GPU.
  arXiv  Detail & Related papers  (2024-11-29T08:10:49Z)
• Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution [151.1255837803585]
  We propose a novel approach, pursuing Spatial Adaptation and Temporal Coherence (SATeCo) for video super-resolution. SATeCo pivots on learning spatial-temporal guidance from low-resolution videos to calibrate both latent-space high-resolution video denoising and pixel-space video reconstruction. Experiments conducted on the REDS4 and Vid4 datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-03-25T17:59:26Z)
• VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis [73.50359502037232]
  VoxNeRF is a novel approach to enhance the quality and efficiency of neural indoor reconstruction and novel view synthesis.<n>We propose an efficient voxel-guided sampling technique that allocates computational resources to selectively the most relevant segments of rays.<n>Our approach is validated with extensive experiments on ScanNet and ScanNet++.
  arXiv  Detail & Related papers  (2023-11-09T11:32:49Z)
• HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging [138.04956118993934]
  We propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy.
  arXiv  Detail & Related papers  (2022-03-04T06:37:45Z)
• Monocular Real-Time Volumetric Performance Capture [28.481131687883256]
  We present the first approach to volumetric performance capture and novel-view rendering at real-time speed from monocular video. Our system reconstructs a fully textured 3D human from each frame by leveraging Pixel-Aligned Implicit Function (PIFu) We also introduce an Online Hard Example Mining (OHEM) technique that effectively suppresses failure modes due to the rare occurrence of challenging examples.
  arXiv  Detail & Related papers  (2020-07-28T04:45:13Z)
• Video Face Super-Resolution with Motion-Adaptive Feedback Cell [90.73821618795512]
  Video super-resolution (VSR) methods have recently achieved a remarkable success due to the development of deep convolutional neural networks (CNN) In this paper, we propose a Motion-Adaptive Feedback Cell (MAFC), a simple but effective block, which can efficiently capture the motion compensation and feed it back to the network in an adaptive way.
  arXiv  Detail & Related papers  (2020-02-15T13:14:10Z)
• End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation [19.67999205691758]
  Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart. We propose a novel dynamic local filter network to perform implicit motion estimation and compensation. We also propose a global refinement network based on ResBlock and autoencoder structures.
  arXiv  Detail & Related papers  (2020-01-05T03:47:24Z)

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.