Feature-based Synthesis Research Articles

MVFSIGM: multi-variant feature-based synthesis image generation model for improved stability using generative adversarial network

MVFSIGM: multi-variant feature-based synthesis image generation model for improved stability using generative adversarial network

Evaluating Designer Learning and Performance in Interactive Deep Generative Design

Abstract Deep generative models have shown significant promise in improving performance in design space exploration. But there is limited understanding of their interpretability, a necessity when model explanations are desired and problems are ill-defined. Interpretability involves learning design features behind design performance, called designer learning. This study explores human–machine collaboration’s effects on designer learning and design performance. We conduct an experiment (N = 42) designing mechanical metamaterials using a conditional variational autoencoder. The independent variables are: (i) the level of automation of design synthesis, e.g., manual (where the user manually manipulates design variables), manual feature-based (where the user manipulates the weights of the features learned by the encoder), and semi-automated feature-based (where the agent generates a local design based on a start design and user-selected step size); and (ii) feature semanticity, e.g., meaningful versus abstract features. We assess feature-specific learning using item response theory and design performance using utopia distance and hypervolume improvement. The results suggest that design performance depends on the subjects’ feature-specific knowledge, emphasizing the precursory role of learning. The semi-automated synthesis locally improves the utopia distance. Still, it does not result in higher global hypervolume improvement compared to manual design synthesis and reduced designer learning compared to manual feature-based synthesis. The subjects learn semantic features better than abstract features only when design performance is sensitive to them. Potential cognitive constructs influencing learning in human–machine collaborative settings are discussed, such as cognitive load and recognition heuristics.

Deep Residual Architecture Using Pixel and Feature Cues for View Synthesis and Temporal Interpolation

In this paper, we propose a deep residual architecture that can be used both for synthesizing high quality angular views in light fields and temporal frames in classical videos. The proposed framework consists of an optical flow estimator optimized for view synthesis, a trainable feature extractor and a residual convolutional network for pixel and feature-based view reconstruction. Among these modules, the fine-tuning of the optical flow estimator specifically for the view synthesis task yields scene depth or motion information that is well optimized for the targeted problem. In cooperation with the end-to-end trainable encoder, the synthesis block employs both pixel-based and feature-based synthesis with residual connection blocks, and the two synthesized views are fused with the help of a learned soft mask to obtain the final reconstructed view. Experimental results with various datasets show that our method performs favorably against other state-of-the-art (SOTA) methods with a large gain for light field view synthesis. Furthermore, with a little modification, our method can also be used for video frame interpolation, generating high quality frames compared with SOTA interpolation methods.

An intelligent feature-based process planning system for prismatic parts

Today, feature-based design has become a core technology for solid product modelling primarily because it can capture the designer's intent and provide the capability to satisfy the informational needs of the down-line application tasks for CAD/CAM integration. This paper reports the development of an intelligent environment, IFPP (Intelligent Feature-based Process Planning), for the feature-based design synthesis and process planning of prismatic parts to be produced on CNC machining centres. IFPP consists of two functional modules, namely Feature Based Modeller (FBM) and Automatic process Planner (AutoPlan). The FBM provides a graphical environment for the feature-based synthesis, validation and representation of the solid model of the part to be produced. AutoPlan maps this feature information to the corresponding machining processes to generate the operation plan and corresponding CNC code. This CNC code is unique in that it is functionally encapsulated with the feature data to provide a 'Variant' strategy utilizing the special parametric programming facilities provided on the controller. IFPP thus demonstrates an integrated part-process environment that enables quick turnaround from design to manufacture.