EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors
Transformer is popular in recent 3D human pose estimation, which utilizes long-term modeling to lift 2D keypoints into the 3D space. However, current transformer-based methods do not fully exploit the prior knowledge of the human skeleton provided by the kinematic structure. In this paper, we propose a novel transformer-based model EvoPose to introduce the human body prior knowledge for 3D human pose estimation effectively. Specifically, a Structural Priors Representation (SPR) module represents human priors as structural features carrying rich body patterns, e.g. joint relationships. The structural features are interacted with 2D pose sequences and help the model to achieve more informative spatiotemporal features. Moreover, a Recursive Refinement (RR) module is applied to refine the 3D pose outputs by utilizing estimated results and further injects human priors simultaneously. Extensive experiments demonstrate the effectiveness of EvoPose which achieves a new state of the art on two most popular benchmarks, Human3.6M and MPI-INF-3DHP.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Human Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks. Hypothesizing that neural ar…
2D Human Pose EstimationKeypoint DetectionMulti-Person Pose EstimationNeural Architecture Search+1Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans
Recursive processing is considered a hallmark of human linguistic abilities. A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance le…
Can Transformers Process Recursive Nested Constructions, Like Humans?
Recursive processing is considered a hallmark of human linguistic abilities. A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance le…
Event-based Monocular Dense Depth Estimation with Recurrent Transformers
Event cameras, offering high temporal resolutions and high dynamic ranges, have brought a new perspective to address common challenges (e.g., motion blur and low light) in monocular depth estimation. However, how to effe…
DecoderDepth EstimationEvent-based visionGPU+1Pushdown Layers: Encoding Recursive Structure in Transformer Language Models
Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly cap…
text-classificationText Classification