Synthetic-to-Real Pose Estimation with Geometric Reconstruction

Authors: Qiuxia Lin, Kerui Gu, Linlin Yang, Angela Yao

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4 Experiments4.1 Datasets & Evaluation Metric4.2 Implementation Details4.3 Comparison with the State-of-the-Art4.4 AnalysisTable 1: Hand 2D keypoint detection. Our method has the best average PCK@0.05 on both datasets and the most significant improvements on MCP and Fin.
Researcher Affiliation Academia 1Department of Computer Science, National University of Singapore 2State Key Laboratory of Media Convergence and Communication, CUC 3School of Information and Communication Engineering, CUC {qiuxia, keruigu, ayao}@comp.nus.edu.sg
Pseudocode No No structured pseudocode or algorithm blocks are present in the paper.
Open Source Code No No concrete access to source code for the methodology described in this paper is provided.
Open Datasets Yes For the source domain, we consider the synthetic dataset RHD [43] with 44k rendered images for training. For the unlabeled target domain, we consider real-world datasets H3D [41] and MVHand [39]... SURREAL [31] is a synthetic human dataset... Human3.6M [8] annotates 3.6 million real-world indoor human poses. 3DPW [32] is a challenging outdoor dataset...
Dataset Splits Yes For the unlabeled target domain, we consider real-world datasets H3D [41] and MVHand [39]; these have 11k/2k and 42k/42k training/testing splits respectively... Human3.6M [8]... We follow protocol 1, using S1 and S5-S8 for training and S9 and S11 for testing. 3DPW [32] is a challenging outdoor dataset with 24 videos for training and 24 videos for testing.
Hardware Specification No No specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running experiments are provided.
Software Dependencies No The paper mentions ResNet-101 and Adam optimizer but does not provide specific version numbers for any software dependencies or libraries.
Experiment Setup Yes The initial learning rate is 1e-4, and we used Adam optimizer and degraded the learning rate with 0.1 at steps 60 and 75. Pre-training is done with a batch size of 64 for 40 epochs; fine-tuning is done with a batch size of 32 for 80 epochs. The hyperparameters λa, λr, λp are set as 0.1.