Transformer Network for 3D Human Pose Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current 3D human pose estimation from single images faces challenges due to the need for manual encoding of joint relationships and over-smoothing issues in graph convolutional networks, limiting their ability to accurately estimate 3D poses from diverse datasets without leveraging spatial relationships effectively.

Innovation Solution

A transformer-based neural network architecture that includes a joint embedding mechanism, a joint transformer for predicting intermediate 3D joints and errors, and a refinement transformer for estimating final 3D joints, allowing the network to learn correlations between joints dynamically without manual encoding, and using error prediction and intermediate supervision to refine predictions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If graph convolutional networks are used for 3D pose estimation, then spatial relationships between joints can be modeled, but manual encoding of joint relationships is required which increases device complexity

Engineering Contradiction:
Improve3D pose estimation accuracyVSAvoidmanual encoding of joint relationships
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The transformer-based network automatically learns and encodes the kinematic relationships between joints through self-attention mechanisms, eliminating the need for manual encoding of adjacency matrices. The network serves itself by discovering joint relationships directly from the data during training, rather than requiring pre-defined graph structures.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical graph convolutional approach with a transformer-based attention mechanism. Instead of using fixed graph structures with manual adjacency matrices, the system uses dynamic self-attention to model joint relationships, substituting the rigid mechanical graph structure with a more flexible attention-based system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If multiple graph convolutional network layers are stacked to improve pose estimation, then spatial relationships are better captured, but over-smoothing occurs which degrades performance

Engineering Contradiction:
Improvespatial relationships captureVSAvoidover-smoothing effect
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent substitutes the graph convolutional network architecture with a transformer-based architecture that uses self-attention mechanisms. This replacement avoids the over-smoothing problem inherent in stacked GCN layers while maintaining the ability to capture spatial relationships between joints through attention weights that dynamically model joint dependencies.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The transformer-based system introduces dynamic attention mechanisms that adaptively weight the importance of different joint relationships based on the input pose, rather than applying fixed convolutional operations. This dynamic approach allows the model to capture spatial relationships without the degradation caused by repeated convolutional layers.

Inventive Principle:
Principle #15Dynamics

3Device complexity

If standard graph convolutions with shared weight matrices are used, then model simplicity is maintained, but the ability to model different relationships between body joints is limited

Engineering Contradiction:
Improveshared weight matrix structureVSAvoidmodeling different body joint relationships
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The transformer-based network applies local quality by allowing different attention mechanisms to operate on different joint pairs, enabling the model to capture unique relationships between specific body joints. Each joint can have its own attention pattern, allowing the system to model diverse relationships across different body parts rather than applying a uniform shared weight matrix.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system transitions from static shared weight matrices to dynamic attention mechanisms that adaptively adjust the importance of different joint relationships based on the input context. This allows the model to flexibly model different body joint relationships without being constrained by a fixed weight structure.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4310783A1Transformer based neural network for 3D human pose estimation
Publication Date: 2024.01.24 THE PROVOST FELLOWS FOUNDATION SCHOLARS AND THE OTHER MEMBERS OF BOARD OF THE COLLEGE OF THE HOLY AND UNDIVIDED TRINITY OF QUEEN ELIZABETH NEAR DUBLIN
  • EP4310783A1 patent drawingFigure 1A
  • EP4310783A1 patent drawingFigure 1B
  • EP4310783A1 patent drawingFigure 2

AI summary

Disclosed is a transformer based neural network architecture for estimating a 3D pose from a 2D pose, that includes a joint embedding mechanism for receiving a plurality of 2D joint positions, setting each 2D joint position as a token, and increasing a dimension of each token to a predefined higher dimension. The transformer based neural network architecture further includes a joint transformer communicatively coupled to the joint embedding mechanism, for predicting a plurality of intermediate 3D joints, and a corresponding plurality of prediction errors, from corresponding plurality of tokens of the increased dimension, and a refinement transformer for estimating a plurality of final 3D joints based on the plurality of intermediate 3D joints, and corresponding plurality of prediction errors, wherein the plurality of final 3D joints is concatenated to generate the 3D pose.