Alert button
Picture for Gleb Gusev

Gleb Gusev

Alert button

SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines

Aug 30, 2023
Dimitrios Mallis, Sk Aziz Ali, Elona Dupont, Kseniya Cherenkova, Ahmet Serdar Karadeniz, Mohammad Sadil Khan, Anis Kacem, Gleb Gusev, Djamila Aouada

Figure 1 for SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines
Figure 2 for SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines
Figure 3 for SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines
Figure 4 for SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines

Recent breakthroughs in geometric Deep Learning (DL) and the availability of large Computer-Aided Design (CAD) datasets have advanced the research on learning CAD modeling processes and relating them to real objects. In this context, 3D reverse engineering of CAD models from 3D scans is considered to be one of the most sought-after goals for the CAD industry. However, recent efforts assume multiple simplifications limiting the applications in real-world settings. The SHARP Challenge 2023 aims at pushing the research a step closer to the real-world scenario of CAD reverse engineering through dedicated datasets and tracks. In this paper, we define the proposed SHARP 2023 tracks, describe the provided datasets, and propose a set of baseline methods along with suitable evaluation metrics to assess the performance of the track solutions. All proposed datasets along with useful routines and the evaluation metrics are publicly available.

Viaarxiv icon

SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes

Apr 13, 2023
Kseniya Cherenkova, Elona Dupont, Anis Kacem, Ilya Arzhannikov, Gleb Gusev, Djamila Aouada

Figure 1 for SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes
Figure 2 for SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes
Figure 3 for SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes
Figure 4 for SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes

3D scanning as a technique to digitize objects in reality and create their 3D models, is used in many fields and areas. Though the quality of 3D scans depends on the technical characteristics of the 3D scanner, the common drawback is the smoothing of fine details, or the edges of an object. We introduce SepicNet, a novel deep network for the detection and parametrization of sharp edges in 3D shapes as primitive curves. To make the network end-to-end trainable, we formulate the curve fitting in a differentiable manner. We develop an adaptive point cloud sampling technique that captures the sharp features better than uniform sampling. The experiments were conducted on a newly introduced large-scale dataset of 50k 3D scans, where the sharp edge annotations were extracted from their parametric CAD models, and demonstrate significant improvement over state-of-the-art methods.

Viaarxiv icon

CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations

Aug 22, 2022
Elona Dupont, Kseniya Cherenkova, Anis Kacem, Sk Aziz Ali, Ilya Arzhannikov, Gleb Gusev, Djamila Aouada

Figure 1 for CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations
Figure 2 for CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations
Figure 3 for CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations
Figure 4 for CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations

3D reverse engineering is a long sought-after, yet not completely achieved goal in the Computer-Aided Design (CAD) industry. The objective is to recover the construction history of a CAD model. Starting from a Boundary Representation (B-Rep) of a CAD model, this paper proposes a new deep neural network, CADOps-Net, that jointly learns the CAD operation types and the decomposition into different CAD operation steps. This joint learning allows to divide a B-Rep into parts that were created by various types of CAD operations at the same construction step; therefore providing relevant information for further recovery of the design history. Furthermore, we propose the novel CC3D-Ops dataset that includes over $37k$ CAD models annotated with CAD operation type labels and step labels. Compared to existing datasets, the complexity and variety of CC3D-Ops models are closer to those used for industrial purposes. Our experiments, conducted on the proposed CC3D-Ops and the publicly available Fusion360 datasets, demonstrate the competitive performance of CADOps-Net with respect to state-of-the-art, and confirm the importance of the joint learning of CAD operation types and steps.

Viaarxiv icon

Towards Computationally Feasible Deep Active Learning

May 07, 2022
Akim Tsvigun, Artem Shelmanov, Gleb Kuzmin, Leonid Sanochkin, Daniil Larionov, Gleb Gusev, Manvel Avetisian, Leonid Zhukov

Figure 1 for Towards Computationally Feasible Deep Active Learning
Figure 2 for Towards Computationally Feasible Deep Active Learning
Figure 3 for Towards Computationally Feasible Deep Active Learning
Figure 4 for Towards Computationally Feasible Deep Active Learning

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many others. One of such problems is the excessive computational resources required to train an acquisition model and estimate its uncertainty on instances in the unlabeled pool. We propose two techniques that tackle this issue for text classification and tagging tasks, offering a substantial reduction of AL iteration duration and the computational overhead introduced by deep acquisition models in AL. We also demonstrate that our algorithm that leverages pseudo-labeling and distilled models overcomes one of the essential obstacles revealed previously in the literature. Namely, it was shown that due to differences between an acquisition model used to select instances during AL and a successor model trained on the labeled data, the benefits of AL can diminish. We show that our algorithm, despite using a smaller and faster acquisition model, is capable of training a more expressive successor model with higher performance.

* Accepted at NAACL-2022 Findings 
Viaarxiv icon

Adversarial Attacks on Deep Models for Financial Transaction Records

Jun 15, 2021
Ivan Fursov, Matvey Morozov, Nina Kaploukhaya, Elizaveta Kovtun, Rodrigo Rivera-Castro, Gleb Gusev, Dmitry Babaev, Ivan Kireev, Alexey Zaytsev, Evgeny Burnaev

Figure 1 for Adversarial Attacks on Deep Models for Financial Transaction Records
Figure 2 for Adversarial Attacks on Deep Models for Financial Transaction Records
Figure 3 for Adversarial Attacks on Deep Models for Financial Transaction Records
Figure 4 for Adversarial Attacks on Deep Models for Financial Transaction Records

Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their tremendous number of parameters and limited robustness. In particular, deep-learning models are vulnerable to adversarial attacks: a little change in the input harms the model's output. In this work, we examine adversarial attacks on transaction records data and defences from these attacks. The transaction records data have a different structure than the canonical NLP or time series data, as neighbouring records are less connected than words in sentences, and each record consists of both discrete merchant code and continuous transaction amount. We consider a black-box attack scenario, where the attack doesn't know the true decision model, and pay special attention to adding transaction tokens to the end of a sequence. These limitations provide more realistic scenario, previously unexplored in NLP world. The proposed adversarial attacks and the respective defences demonstrate remarkable performance using relevant datasets from the financial industry. Our results show that a couple of generated transactions are sufficient to fool a deep-learning model. Further, we improve model robustness via adversarial training or separate adversarial examples detection. This work shows that embedding protection from adversarial attacks improves model robustness, allowing a wider adoption of deep models for transaction records in banking and finance.

Viaarxiv icon

PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D

Jan 12, 2021
Kseniya Cherenkova, Djamila Aouada, Gleb Gusev

Figure 1 for PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D
Figure 2 for PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D
Figure 3 for PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D
Figure 4 for PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D

We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data autoencoder. To demonstrate its efficiency we learn to synthesize high-resolution point clouds of 10k points that densely describe the underlying geometry of Computer Aided Design (CAD) models. Scanning artifacts, such as protrusions, missing parts, smoothed edges and holes, inevitably appear in real 3D scans of fabricated CAD objects. Learning the original CAD model construction from a 3D scan requires a ground truth to be available together with the corresponding 3D scan of an object. To solve the gap, we introduce a new dedicated dataset, the CC3D, containing 50k+ pairs of CAD models and their corresponding 3D meshes. This dataset is used to learn a convolutional autoencoder for point clouds sampled from the pairs of 3D scans - CAD models. The challenges of this new dataset are demonstrated in comparison with other generative point cloud sampling models trained on ShapeNet. The CC3D autoencoder is efficient with respect to memory consumption and training time as compared to stateof-the-art models for 3D data generation.

* 2020 IEEE International Conference on Image Processing (ICIP), 2020, pp. 2741-2745  
* 2020 IEEE International Conference on Image Processing (ICIP) 
Viaarxiv icon

SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results

Oct 26, 2020
Alexandre Saint, Anis Kacem, Kseniya Cherenkova, Konstantinos Papadopoulos, Julian Chibane, Gerard Pons-Moll, Gleb Gusev, David Fofi, Djamila Aouada, Bjorn Ottersten

Figure 1 for SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results
Figure 2 for SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results
Figure 3 for SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results
Figure 4 for SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results

The SHApe Recovery from Partial textured 3D scans challenge, SHARP 2020, is the first edition of a challenge fostering and benchmarking methods for recovering complete textured 3D scans from raw incomplete data. SHARP 2020 is organised as a workshop in conjunction with ECCV 2020. There are two complementary challenges, the first one on 3D human scans, and the second one on generic objects. Challenge 1 is further split into two tracks, focusing, first, on large body and clothing regions, and, second, on fine body details. A novel evaluation metric is proposed to quantify jointly the shape reconstruction, the texture reconstruction and the amount of completed data. Additionally, two unique datasets of 3D scans are proposed, to provide raw ground-truth data for the benchmarks. The datasets are released to the scientific community. Moreover, an accompanying custom library of software routines is also released to the scientific community. It allows for processing 3D scans, generating partial data and performing the evaluation. Results of the competition, analysed in comparison to baselines, show the validity of the proposed evaluation metrics, and highlight the challenging aspects of the task and of the datasets. Details on the SHARP 2020 challenge can be found at https://cvi2.uni.lu/sharp2020/.

* SHARP workshop, ECCV 2020 
Viaarxiv icon

Event sequence metric learning

Feb 19, 2020
Dmitrii Babaev, Ivan Kireev, Nikita Ovsov, Mariya Ivanova, Gleb Gusev, Alexander Tuzhilin

Figure 1 for Event sequence metric learning
Figure 2 for Event sequence metric learning
Figure 3 for Event sequence metric learning
Figure 4 for Event sequence metric learning

In this paper we consider a challenging problem of learning discriminative vector representations for event sequences generated by real-world users. Vector representations map behavioral client raw data to the low-dimensional fixed-length vectors in the latent space. We propose a novel method of learning those vector embeddings based on metric learning approach. We propose a strategy of raw data subsequences generation to apply a metric learning approach in a fully self-supervised way. We evaluated the method over several public bank transactions datasets and showed that self-supervised embeddings outperform other methods when applied to downstream classification tasks. Moreover, embeddings are compact and provide additional user privacy protection.

Viaarxiv icon

Minimal Variance Sampling in Stochastic Gradient Boosting

Oct 29, 2019
Bulat Ibragimov, Gleb Gusev

Figure 1 for Minimal Variance Sampling in Stochastic Gradient Boosting
Figure 2 for Minimal Variance Sampling in Stochastic Gradient Boosting
Figure 3 for Minimal Variance Sampling in Stochastic Gradient Boosting
Figure 4 for Minimal Variance Sampling in Stochastic Gradient Boosting

Stochastic Gradient Boosting (SGB) is a widely used approach to regularization of boosting models based on decision trees. It was shown that, in many cases, random sampling at each iteration can lead to better generalization performance of the model and can also decrease the learning time. Different sampling approaches were proposed, where probabilities are not uniform, and it is not currently clear which approach is the most effective. In this paper, we formulate the problem of randomization in SGB in terms of optimization of sampling probabilities to maximize the estimation accuracy of split scoring used to train decision trees. This optimization problem has a closed-form nearly optimal solution, and it leads to a new sampling technique, which we call Minimal Variance Sampling (MVS). The method both decreases the number of examples needed for each iteration of boosting and increases the quality of the model significantly as compared to the state-of-the art sampling methods. The superiority of the algorithm was confirmed by introducing MVS as a new default option for subsampling in CatBoost, a gradient boosting library achieving state-of-the-art quality on various machine learning tasks.

Viaarxiv icon

Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling

Jun 20, 2019
Valentina Fedorova, Gleb Gusev, Pavel Serdyukov

Figure 1 for Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling
Figure 2 for Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling
Figure 3 for Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling
Figure 4 for Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling

We study the problem of aggregation noisy labels. Usually, it is solved by proposing a stochastic model for the process of generating noisy labels and then estimating the model parameters using the observed noisy labels. A traditional assumption underlying previously introduced generative models is that each object has one latent true label. In contrast, we introduce a novel latent distribution assumption, implying that a unique true label for an object might not exist, but rather each object might have a specific distribution generating a latent subjective label each time the object is observed. Our experiments showed that the novel assumption is more suitable for difficult tasks, when there is an ambiguity in choosing a "true" label for certain objects.

Viaarxiv icon