“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Additive manufacturing enables the printing of metallic parts, such as customized implants for patients, durable single-crystal parts for use in harsh environments, and the printing of parts with site-specific chemical compositions and properties from 3D designs. However, the selection of alloys, printing processes and process variables results in an exceptional diversity of microstructures, properties and defects that affect the serviceability of the printed parts. Control of these attributes using the rich knowledge base of metallurgy remains a challenge because of the complexity of the printing process. Transforming 3D designs created in the virtual world into high-quality products in the physical world needs a new methodology not commonly used in traditional manufacturing. Rapidly developing powerful digital tools such as mechanistic models and machine learning, when combined with the knowledge base of metallurgy, have the potential to shape the future of metal printing. Starting from product design to process planning and process monitoring and control, these tools can help improve microstructure and properties, mitigate defects, automate part inspection and accelerate part qualification. Here, we examine advances in metal printing focusing on metallurgy, as well as the use of mechanistic models and machine learning and the role they play in the expansion of the additive manufacturing of metals. Several key industries routinely use metal printing to make complex parts that are difficult to produce by conventional manufacturing. Here, we show that a synergistic combination of metallurgy, mechanistic models and machine learning is driving the continued growth of metal printing.

Metallurgy, mechanistic models and machine learning in metal printing

ICIP is the premier international forum for the technological advances and research results in the fields of theoretical, experimental, and applied image and video processing. The series is sponsored by the IEEE Signal Processing Society and has been held annually since 1994. Research frontiers in fields ranging from traditional image processing applications to evolving multimedia and video technologies are regularly advanced by results first reported in ICIP technical sessions. Topics include, but are not limited to: Procedure 1. Send notice of intent to bid to the Vice President – Conferences and SPS Conference Services staff at sps-conf-proposals@ieee.org. Include in the notice your contact information and the proposed dates and location. 2. Conference Services staff will issue the proposal submission forms upon receipt of the letter of intent. 3. The forms must be completed and the proposal submitted to the Conference Services staff at least three months prior to the next ICIP meeting. See below for more information on the Proposal Timeline. 4. The receipt of the proposal may prompt an invitation to present from the IVMSP Technical Committee Chair to the Committee. 5. The IVMSP Technical Committee will review the proposal, and if it so chooses, will endorse the proposal and forward it to the Conference Board. 6. The Vice President – Conferences may issue an invitation to present to the Conference Board. 7. The Conference Board, if it so chooses, will endorse the proposal and forward it to the Board of Governors for final approval.

IEEE International Conference on Image Processing (ICIP)

This paper presents a new method to fabricate 3D models on a robotic printing system equipped with multi-axis motion. Materials are accumulated inside the volume along curved tool-paths so that the need of supporting structures can be tremendously reduced - if not completely abandoned - on all models. Our strategy to tackle the challenge of tool-path planning for multi-axis 3D printing is to perform two successive decompositions, first volume-to-surfaces and then surfaces-to-curves. The volume-to-surfaces decomposition is achieved by optimizing a scalar field within the volume that represents the fabrication sequence. The field is constrained such that its iso-values represent curved layers that are supported from below, and present a convex surface affording for collision-free navigation of the printer head. After extracting all curved layers, the surfaces-to-curves decomposition covers them with tool-paths while taking into account constraints from the robotic printing system. Our method successfully generates tool-paths for 3D printing models with large overhangs and high-genus topology. We fabricated several challenging cases on our robotic platform to verify and demonstrate its capabilities.

/pdf/support-free-volume-printing-by-multi-axis-motion-4se0f5jf9v.pdf

Support-free volume printing by multi-axis motion

Inspired by natural cellular materials such as trabecular bone, lattice structures have been developed as a new type of lightweight material. In this paper we present a novel method to design lattice structures that conform with both the principal stress directions and the boundary of the optimized shape. Our method consists of two major steps: the first optimizes concurrently the shape (including its topology) and the distribution of orthotropic lattice materials inside the shape to maximize stiffness under application-specific external loads; the second takes the optimized configuration (i.e., locally-defined orientation, porosity, and anisotropy) of lattice materials from the previous step, and extracts a globally consistent lattice structure by field-aligned parameterization. Our approach is robust and works for both 2D planar and 3D volumetric domains. Numerical results and physical verifications demonstrate remarkable structural properties of conforming lattice structures generated by our method.

Design and Optimization of Conforming Lattice Structures

Face anti-spoofing is crucial to security of face recognition systems. Previous approaches focus on developing discriminative models based on the features extracted from images, which may be still entangled between spoof patterns and real persons. In this paper, motivated by the disentangled representation learning, we propose a novel perspective of face anti-spoofing that disentangles the liveness features and content features from images, and the liveness features is further used for classification. We also put forward a Convolutional Neural Network (CNN) architecture with the process of disentanglement and combination of low-level and high-level supervision to improve the generalization capabilities. We evaluate our method on public benchmark datasets and extensive experimental results demonstrate the effectiveness of our method against the state-of-the-art competitors. Finally, we further visualize some results to help understand the effect and advantage of disentanglement.

Face Anti-Spoofing via Disentangled Representation Learning

Additive manufacturing enables the fabrication of objects embedding meta-materials. By creating fine-scale structures, the object's physical properties can be graded (e.g. elasticity, porosity), even though a single base material is used for fabrication. Designing the fine and detailed geometry of a metamaterial while attempting to achieve specific properties is difficult. In addition, the structures are intended to fill comparatively large volumes, which quickly leads to large data structures and intractable simulation costs. Thus, most metamaterials are defined as periodic structures repeated in regular lattices. The periodicity simplifies modeling, simulation, and reduces memory costs - however it limits the possibility to smoothly grade properties along free directions. In this work, we propose a novel metamaterial with controllable, freely orientable, orthotropic elastic behavior - orthotropy means that elasticity is controlled independently along three orthogonal axes, which leads to materials that better adapt to uneven, directional load scenarios, and offer a more versatile material design primitive. The fine-scale structures are generated procedurally by a stochastic process, and resemble a foam. The absence of global organization and periodicity allows the free gradation of density, orientation, and stretch, leading to the controllable orthotropic behavior. The procedural nature of the synthesis process allows it to scale to arbitrarily large volumes at low memory costs. We detail the foam structure synthesis, analyze and discuss its properties through numerical and experimental verifications, and finally demonstrate the use of orthotropic materials for the design of 3D printed objects.

/pdf/orthotropic-k-nearest-foams-for-additive-manufacturing-mv3m1k23j8.pdf

Orthotropic k-nearest foams for additive manufacturing

A critical advantage of additive manufacturing is its ability to fabricate complex small-scale structures. These microstructures can be understood as a metamaterial: they exist at a much smaller scale than the volume they fill, and are collectively responsible for an average elastic behavior different from that of the base printing material making the fabricated object lighter and/or flexible along specific directions. In addition, the average behavior can be graded spatially by progressively modifying the micro structure geometry. The definition of a microstructure is a careful trade-off between the geometric requirements of manufacturing and the properties one seeks to obtain within a shape: in our case a wide range of elastic behaviors. Most existing microstructures are designed for stereolithography (SLA) and laser sintering (SLS) processes. The requirements are however different than those of continuous deposition systems such as fused filament fabrication (FFF), for which there is currently a lack of microstructures enabling graded elastic behaviors. In this work we introduce a novel type of microstructures that strictly enforce all the requirements of FFF-like processes: continuity, self-support and overhang angles. They offer a range of orthotropic elastic responses that can be graded spatially. This allows to fabricate parts usually reserved to the most advanced technologies on widely available inexpensive printers that also benefit from a continuously expanding range of materials.

/pdf/polyhedral-voronoi-diagrams-for-additive-manufacturing-1tg7358996.pdf

Polyhedral voronoi diagrams for additive manufacturing

Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale supervision on intermediate layers. In this paper, we bring the first omni-scale supervision method to point cloud segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR), where target Receptive Field Component Codes (RFCCs) are designed to record categories within receptive fields for hidden units in the encoder. Then, target RFCCs will supervise the decoder to gradually infer the RFCCs in a coarse-to-fine categories reasoning manner, and finally obtain the semantic labels. Because many hidden features are inactive with tiny magnitude and make minor contributions to RFCC prediction, we propose a Feature Densification with a centrifugal potential to obtain more unambiguous features, and it is in effect equivalent to entropy regularization over features. More active features can further unleash the potential of our omni-supervision method. We embed our method into four prevailing backbones and test on three challenging benchmarks. Our method can significantly improve the backbones in all three datasets. Specifically, our method brings new state-of-the-art performances for S3DIS as well as Semantic3D and ranks the 1st in the ScanNet benchmark among all the point-based methods. Code is publicly available at https://github.com/azuki-miho/RFCR.

/pdf/omni-supervised-point-cloud-segmentation-via-gradual-3wxtvargth.pdf

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Layered manufacturing inherently suffers from staircase defects along surfaces that are gently slopped with respect to the build direction. Reducing the slice thickness improves the situation but never resolves it completely as flat layers remain a poor approximation of the true surface in these regions. In addition, reducing the slice thickness largely increases the print time.In this work we focus on a simple yet effective technique to improve the print accuracy for layered manufacturing by filament deposition. Our method works with standard three-axis 3D filament printers (e.g.the typical, widely available 3D printers), using standard extrusion nozzles. It better reproduces the geometry of sloped surfaces without increasing the print time.Our key idea is to perform a local anti-aliasing, working at a sub-layer accuracy to produce slightly curved deposition paths and reduce approximation errors. This is inspired by Computer Graphics anti-aliasing techniques which consider sub-pixel precision to treat aliasing effects. We show that the necessary deviation in height compared to standard slicing is bounded by half the layer thickness. Therefore, the height changes remain small and plastic deposition remains reliable. We further split and order paths to minimize defects due to the extruder nozzle shape, avoiding any change to the existing hardware. We apply and analyze our approach on 3D printed examples, showing that our technique greatly improves surface accuracy and silhouette quality while keeping the print time nearly identical. Propose a technique reduces staircase defects for layered manufacturing by FDM.It is achieved by slightly curved deposition paths within feasible thickness bounds.We also minimize nozzle interference by path splitting and ordering.The print time remains nearly identical.This approach is compatible with existing slicers and adaptive slicing.

Haichuan Song

Papers

Face Anti-Spoofing via Disentangled Representation Learning

Orthotropic k-nearest foams for additive manufacturing

Polyhedral voronoi diagrams for additive manufacturing

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Anti-aliasing for fused filament deposition