Research map / 3D vision / Human pose estimation
Deep Globally Constrained MRFs for Human Pose Estimation
Ioannis Marras, Petar Palasek, Ioannis Patras
This paper tried a common change: Add data augmentation
use the proposed data augmentation instead of that of Tompson et al. · MPII (PCK@0.15) · PCK full body: 48.98 -> 49.62 Improved
What 689 accepted papers report for this change
- 560 improved
- 44 no clear effect
- 26 mixed
- 59 hurt
- Understanding Multimodal Learning: A Loss Landscape Smoothness Perspective ICML 2026 · add data augmentation (jitter, crop, flip) · UPMC-Food101 · accuracy: 92.84 -> 94.93Improved
- AsyncBEV: Cross-modal flow alignment in Asynchronous 3D Object Detection ICLR 2026 · add EMC + asynchronous data augmentation training · nuScenes val, 0 s offset · NDS: 66.7 -> 63.1Hurt
- Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm ICML 2026 · add data augmentation (5 biographies per individual) in pre-training · Biography PT test, unseen templates · EM: 2.71 -> 81.27Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the MRF spatial model between the coarse and refinement networks (ablation) | coarse+coarse-to-fine model · MPII (PCK@0.15) | PCK full body: 45.71 -> 47.49 | Improved |
| add the coarse-to-fine refinement network to the coarse model (ablation) | coarse model · MPII (PCK@0.15) | PCK full body: 38.71 -> 45.71 | Improved |
| add the coarse-to-fine refinement network to the coarse model (ablation) | coarse model · FashionPose (PCK@0.15) | PCK full body: 84.55 -> 86.95 | Improved |
| add the MRF model to the coarse+refinement pipeline (full model) (ablation) | coarse+coarse-to-fine model · FashionPose (PCK@0.15) | PCK full body: 86.95 -> 90.21 | Improved |
| iterate the MRF inference rather than a single loop (ablation) | full model · MPII (PCK@0.15) | PCK full body: 48.40 -> 49.62 | Improved |
| increase the number of pairwise filters from K=1 to K=4 (ablation) | full model · MPII (PCK@0.15) | PCK full body: 48.60 -> 49.62 | Improved |
| place the MRF before the refinement network instead of after it (ablation) | full model · MPII (PCK@0.15) | PCK full body: 47.49 -> 49.62 | Improved |
| use the proposed data augmentation instead of that of Tompson et al. (ablation) | full model · MPII (PCK@0.15) | PCK full body: 48.98 -> 49.62 | Improved |
| use the proposed larger coarse ConvNet instead of that of Tompson et al. | coarse model · MPII (PCK@0.15) | PCK full body: 36.25 -> 38.71 | Improved |
| use the proposed constrained MRF full model instead of the MRF of Tompson et al. | full model · MPII (PCK@0.15) | PCK full body: 44.08 -> 49.62 | Improved |
Closest papers by meaning
- Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation (ICCV 2017 · similarity 0.90)
- Coarse-To-Fine Volumetric Prediction for Single-Image 3D Human Pose (CVPR 2017 · similarity 0.90)
- Human Pose Estimation Using Global and Local Normalization (ICCV 2017 · similarity 0.89)
- A Simple yet Effective Baseline for 3D Human Pose Estimation (ICCV 2017 · similarity 0.89)
- Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos (CVPR 2017 · similarity 0.88)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
