DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion
3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can severely affect pose estimation. To address these challenges, we introduce the task of Deficiency-Aware 3D Pose Estimation. Traditional 3D pose estimation methods often rely on multi-stage networks and modular combinations, which can lead to cumulative errors and increased training complexity, making them unable to effectively address deficiency-aware estimation. To this end, we propose DeProPose, a flexible method that simplifies the network architecture to reduce training complexity and avoid information loss in multi-stage designs. Additionally, the model innovatively introduces a multi-view feature fusion mechanism based on relative projection error, which effectively utilizes information from multiple viewpoints and dynamically assigns weights, enabling efficient integration and enhanced robustness to overcome deficiency-aware 3D Pose Estimation challenges. Furthermore, to thoroughly evaluate this end-to-end multi-view 3D human pose estimation model and to advance research on occlusion-related challenges, we have developed a novel 3D human pose estimation dataset, termed the Deficiency-Aware 3D Pose Estimation (DA-3DPE) dataset. This dataset encompasses a wide range of deficiency scenarios, including noise interference, missing viewpoints, and occlusion challenges. Compared to state-of-the-art methods, DeProPose not only excels in addressing the deficiency-aware problem but also shows improvement in conventional scenarios, providing a powerful and user-friendly solution for 3D human pose estimation. The source code will be available at https://github.com/WUJINHUAN/DeProPose.
Code (1)
Tasks
3D Human Pose Estimation3D Pose EstimationMulti-view 3D Human Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data
Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling bias. Here we show that pretrained large language models induce risk-…
Revisiting Consensus-Based Energy-Management in Smart Grid with Transmission Losses and Directed Communication
We discovered a deficiency in Algorithm 1 and Theorem 3 of [1]. The algorithm called CEMA aims to solve an energy management problem distributively. However, by means of a counter example, we show that Theorem 2 and 3 of…
energy managementManagementvalidThe Mystery of the Pathological Path-star Task for Language Models
The recently introduced path-star task is a minimal task designed to exemplify limitations to the abilities of language models (Bachmann and Nagarajan, 2024). It involves a path-star graph where multiple arms radiate fro…
On Experiments
The scientific process is a means to turn the results of experiments into knowledge about the world in which we live. Much research effort has been directed toward automating this process. To do this, one needs to formul…
Statistical Deficiency for Task Inclusion Estimation
Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models. The trend is to build general models able to address any task. Even though transfer learning and m…
Transfer Learning