Michael Heizmann

Chengzhi Wu, Kanran Zhou, Jan-Philipp Kaiser et al.

To enable automatic disassembly of different product types with uncertain conditions and degrees of wear in remanufacturing, agile production systems that can adapt dynamically to changing requirements are needed. Machine learning algorithms can be employed due to their generalization capabilities of learning from various types and variants of products. However, in reality, datasets with a diversity of samples that can be used to train models are difficult to obtain in the initial period. This may cause bad performances when the system tries to adapt to new unseen input data in the future. In order to generate large datasets for different learning purposes, in our project, we present a Blender add-on named MotorFactory to generate customized mesh models of various motor instances. MotorFactory allows to create mesh models which, complemented with additional add-ons, can be further used to create synthetic RGB images, depth images, normal images, segmentation ground truth masks, and 3D point cloud datasets with point-wise semantic labels. The created synthetic datasets may be used for various tasks including motor type classification, object detection for decentralized material transfer tasks, part segmentation for disassembly and handling tasks, or even reinforcement learning-based robotics control or view-planning.

Lanxiao Li, Michael Heizmann

Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance between views of the same scene, modality-invariance between depth and RGB images, format-invariance between point clouds and voxels. Although they have achieved promising results, previous researches lack a systematic and fair comparison of these invariances. To address this issue, our work, for the first time, introduces a unified framework, under which various pre-training methods can be investigated. We conduct extensive experiments and provide a closer look at the contributions of different invariances in 3D pre-training. Also, we propose a simple but effective method that jointly pre-trains a 3D encoder and a depth map encoder using contrastive learning. Models pre-trained with our method gain significant performance boost in downstream tasks. For instance, a pre-trained VoteNet outperforms previous methods on SUN RGB-D and ScanNet object detection benchmarks with a clear margin.

Lanxiao Li, Michael Heizmann

To apply transformer-based models to point cloud understanding, many previous works modify the architecture of transformers by using, e.g., local attention and down-sampling. Although they have achieved promising results, earlier works on transformers for point clouds have two issues. First, the power of plain transformers is still under-explored. Second, they focus on simple and small point clouds instead of complex real-world ones. This work revisits the plain transformers in real-world point cloud understanding. We first take a closer look at some fundamental components of plain transformers, e.g., patchifier and positional embedding, for both efficiency and performance. To close the performance gap due to the lack of inductive bias and annotated data, we investigate self-supervised pre-training with masked autoencoder (MAE). Specifically, we propose drop patch, which prevents information leakage and significantly improves the effectiveness of MAE. Our models achieve SOTA results in semantic segmentation on the S3DIS dataset and object detection on the ScanNet dataset with lower computational costs. Our work provides a new baseline for future research on transformers for point clouds.

Lanxiao Li, Michael Heizmann

Capturing and labeling real-world 3D data is laborious and time-consuming, which makes it costly to train strong 3D models. To address this issue, recent works present a simple method by generating randomized 3D scenes without simulation and rendering. Although models pre-trained on the generated synthetic data gain impressive performance boosts, previous works have two major shortcomings. First, they focus on only one downstream task (i.e., object detection), and the generalization to other tasks is unexplored. Second, the contributions of generated data are not systematically studied. To obtain a deeper understanding of the randomized 3D scene generation technique, we revisit previous works and compare different data generation methods using a unified setup. Moreover, to clarify the generalization of the pre-trained models, we evaluate their performance in multiple tasks (i.e., object detection and semantic segmentation) and with different pre-training methods (i.e., masked autoencoder and contrastive learning). Moreover, we propose a new method to generate 3D scenes with spherical harmonics. It surpasses the previous formula-driven method with a clear margin and achieves on-par results with methods using real-world scans and CAD models.

Ali Darijani, Jürgen Beyerer, Zahra Sadat Hajseyed Nasrollah et al.

Probability theory has become the predominant framework for quantifying uncertainty across scientific and engineering disciplines, with a particular focus on measurement and control systems. However, the widespread reliance on simple Gaussian assumptions--particularly in control theory, manufacturing, and measurement systems--can result in incomplete representations and multistage lossy approximations of complex phenomena, including inaccurate propagation of uncertainty through multi stage processes. This work proposes a comprehensive yet computationally tractable framework for representing and propagating quantitative attributes arising in measurement systems using Probability Density Functions (PDFs). Recognizing the constraints imposed by finite memory in software systems, we advocate for the use of Gaussian Mixture Models (GMMs), a principled extension of the familiar Gaussian framework, as they are universal approximators of PDFs whose complexity can be tuned to trade off approximation accuracy against memory and computation. From both mathematical and computational perspectives, GMMs enable high performance and, in many cases, closed form solutions of essential operations in control and measurement. The paper presents practical applications within manufacturing and measurement contexts especially circular factory, demonstrating how the GMMs framework supports accurate representation and propagation of measurement uncertainty and offers improved accuracy--compared to the traditional Gaussian framework--while keeping the computations tractable.

Maximilian Wachter, Sebastian Murgul, Michael Heizmann

Rhythm transcription is a key subtask of notation-level Automatic Music Transcription (AMT). While deep learning models have been extensively used for detecting the metrical grid in audio and MIDI performances, beat-based rhythm quantization remains largely unexplored. In this work, we introduce a novel deep learning approach for quantizing MIDI performances using a priori beat information. Our method leverages the transformer architecture to effectively process synchronized score and performance data for training a quantization model. Key components of our approach include dataset preparation, a beat-based pre-quantization method to align performance and score times within a unified framework, and a MIDI tokenizer tailored for this task. We adapt a transformer model based on the T5 architecture to meet the specific requirements of rhythm quantization. The model is evaluated using a set of score-level metrics designed for objective assessment of quantization performance. Through systematic evaluation, we optimize both data representation and model architecture. Additionally, we apply performance and score augmentations, such as transposition, note deletion, and performance-side time jitter, to enhance the model's robustness. Finally, a qualitative analysis compares our model's quantization performance against state-of-the-art probabilistic and deep-learning models on various example pieces. Our model achieves an onset F1-score of 97.3% and a note value accuracy of 83.3% on the ASAP dataset. It generalizes well across time signatures, including those not seen during training, and produces readable score output. Fine-tuning on instrument-specific datasets further improves performance by capturing characteristic rhythmic and melodic patterns. This work contributes a robust and flexible framework for beat-based MIDI quantization using transformer models.

Chengzhi Wu, Hao Fu, Jan-Philipp Kaiser et al.

The accurate estimation of 6D pose remains a challenging task within the computer vision domain, even when utilizing 3D point cloud data. Conversely, in the manufacturing domain, instances arise where leveraging prior knowledge can yield advancements in this endeavor. This study focuses on the disassembly of starter motors to augment the engineering of product life cycles. A pivotal objective in this context involves the identification and 6D pose estimation of bolts affixed to the motors, facilitating automated disassembly within the manufacturing workflow. Complicating matters, the presence of occlusions and the limitations of single-view data acquisition, notably when motors are placed in a clamping system, obscure certain portions and render some bolts imperceptible. Consequently, the development of a comprehensive pipeline capable of acquiring complete bolt information is imperative to avoid oversight in bolt detection. In this paper, employing the task of bolt detection within the scope of our project as a pertinent use case, we introduce a meticulously devised pipeline. This multi-stage pipeline effectively captures the 6D information with regard to all bolts on the motor, thereby showcasing the effective utilization of prior knowledge in handling this challenging task. The proposed methodology not only contributes to the field of 6D pose estimation but also underscores the viability of integrating domain-specific insights to tackle complex problems in manufacturing and automation.

Anna Hamberger, Sebastian Murgul, Jochen Schmidt et al.

Music transcription plays a pivotal role in Music Information Retrieval (MIR), particularly for stringed instruments like the guitar, where symbolic music notations such as MIDI lack crucial playability information. This contribution introduces the Fretting-Transformer, an encoderdecoder model that utilizes a T5 transformer architecture to automate the transcription of MIDI sequences into guitar tablature. By framing the task as a symbolic translation problem, the model addresses key challenges, including string-fret ambiguity and physical playability. The proposed system leverages diverse datasets, including DadaGP, GuitarToday, and Leduc, with novel data pre-processing and tokenization strategies. We have developed metrics for tablature accuracy and playability to quantitatively evaluate the performance. The experimental results demonstrate that the Fretting-Transformer surpasses baseline methods like A* and commercial applications like Guitar Pro. The integration of context-sensitive processing and tuning/capo conditioning further enhances the model's performance, laying a robust foundation for future developments in automated guitar transcription.

Maximilian Wachter, Sebastian Murgul, Michael Heizmann

We propose a transformer-based rhythm quantization model that incorporates beat and downbeat information to quantize MIDI performances into metrically-aligned, human-readable scores. We propose a beat-based preprocessing method that transfers score and performance data into a unified token representation. We optimize our model architecture and data representation and train on piano and guitar performances. Our model exceeds state-of-the-art performance based on the MUSTER metric.

Sebastian Murgul, Michael Heizmann

Automatic transcription of acoustic guitar fingerpicking performances remains a challenging task due to the scarcity of labeled training data and legal constraints connected with musical recordings. This work investigates a procedural data generation pipeline as an alternative to real audio recordings for training transcription models. Our approach synthesizes training data through four stages: knowledge-based fingerpicking tablature composition, MIDI performance rendering, physical modeling using an extended Karplus-Strong algorithm, and audio augmentation including reverb and distortion. We train and evaluate a CRNN-based note-tracking model on both real and synthetic datasets, demonstrating that procedural data can be used to achieve reasonable note-tracking results. Finetuning with a small amount of real data further enhances transcription accuracy, improving over models trained exclusively on real recordings. These results highlight the potential of procedurally generated audio for data-scarce music information retrieval tasks.

Sebastian Murgul, Johannes Schimper, Michael Heizmann

Automatic transcription of guitar strumming is an underrepresented and challenging task in Music Information Retrieval (MIR), particularly for extracting both strumming directions and chord progressions from audio signals. While existing methods show promise, their effectiveness is often hindered by limited datasets. In this work, we extend a multimodal approach to guitar strumming transcription by introducing a novel dataset and a deep learning-based transcription model. We collect 90 min of real-world guitar recordings using an ESP32 smartwatch motion sensor and a structured recording protocol, complemented by a synthetic dataset of 4h of labeled strumming audio. A Convolutional Recurrent Neural Network (CRNN) model is trained to detect strumming events, classify their direction, and identify the corresponding chords using only microphone audio. Our evaluation demonstrates significant improvements over baseline onset detection algorithms, with a hybrid method combining synthetic and real-world data achieving the highest accuracy for both strumming action detection and chord classification. These results highlight the potential of deep learning for robust guitar strumming transcription and open new avenues for automatic rhythm guitar analysis.

Sebastian Murgul, Michael Heizmann

Beat tracking in musical performance MIDI is a challenging and important task for notation-level music transcription and rhythmical analysis, yet existing methods primarily focus on audio-based approaches. This paper proposes an end-to-end transformer-based model for beat and downbeat tracking in performance MIDI, leveraging an encoder-decoder architecture for sequence-to-sequence translation of MIDI input to beat annotations. Our approach introduces novel data preprocessing techniques, including dynamic augmentation and optimized tokenization strategies, to improve accuracy and generalizability across different datasets. We conduct extensive experiments using the A-MAPS, ASAP, GuitarSet, and Leduc datasets, comparing our model against state-of-the-art hidden Markov models (HMMs) and deep learning-based beat tracking methods. The results demonstrate that our model outperforms existing symbolic music beat tracking approaches, achieving competitive F1-scores across various musical styles and instruments. Our findings highlight the potential of transformer architectures for symbolic beat tracking and suggest future integration with automatic music transcription systems for enhanced music analysis and score generation.

Sebastian Murgul, Moritz Reiser, Michael Heizmann et al.

In this paper, we present a neural network approach for synchronizing audio recordings of human piano performances with their corresponding loosely aligned MIDI files. The task is addressed using a Convolutional Recurrent Neural Network (CRNN) architecture, which effectively captures spectral and temporal features by processing an unaligned piano roll and a spectrogram as inputs to estimate the aligned piano roll. To train the network, we create a dataset of piano pieces with augmented MIDI files that simulate common human timing errors. The proposed model achieves up to 20% higher alignment accuracy than the industry-standard Dynamic Time Warping (DTW) method across various tolerance windows. Furthermore, integrating DTW with the CRNN yields additional improvements, offering enhanced robustness and consistency. These findings demonstrate the potential of neural networks in advancing state-of-the-art MIDI-to-audio alignment.

Ahmed J. Afifi, Samuel T. Thiele, Aldino Rizaldy et al.

The increasing use of deep learning techniques has reduced interpretation time and, ideally, reduced interpreter bias by automatically deriving geological maps from digital outcrop models. However, accurate validation of these automated mapping approaches is a significant challenge due to the subjective nature of geological mapping and the difficulty in collecting quantitative validation data. Additionally, many state-of-the-art deep learning methods are limited to 2D image data, which is insufficient for 3D digital outcrops, such as hyperclouds. To address these challenges, we present Tinto, a multi-sensor benchmark digital outcrop dataset designed to facilitate the development and validation of deep learning approaches for geological mapping, especially for non-structured 3D data like point clouds. Tinto comprises two complementary sets: 1) a real digital outcrop model from Corta Atalaya (Spain), with spectral attributes and ground-truth data, and 2) a synthetic twin that uses latent features in the original datasets to reconstruct realistic spectral data (including sensor noise and processing artifacts) from the ground-truth. The point cloud is dense and contains 3,242,964 labeled points. We used these datasets to explore the abilities of different deep learning approaches for automated geological mapping. By making Tinto publicly available, we hope to foster the development and adaptation of new deep learning tools for 3D applications in Earth sciences. The dataset can be accessed through this link: https://doi.org/10.14278/rodare.2256.

Maximilian Schambach, Jiayang Shi, Michael Heizmann

We present a novel method to reconstruct a spectral central view and its aligned disparity map from spatio-spectrally coded light fields. Since we do not reconstruct an intermediate full light field from the coded measurement, we refer to this as principal reconstruction. The coded light fields correspond to those captured by a light field camera in the unfocused design with a spectrally coded microlens array. In this application, the spectrally coded light field camera can be interpreted as a single-shot spectral depth camera. We investigate several multi-task deep learning methods and propose a new auxiliary loss-based training strategy to enhance the reconstruction performance. The results are evaluated using a synthetic as well as a new real-world spectral light field dataset that we captured using a custom-built camera. The results are compared to state-of-the art compressed sensing reconstruction and disparity estimation. We achieve a high reconstruction quality for both synthetic and real-world coded light fields. The disparity estimation quality is on par with or even outperforms state-of-the-art disparity estimation from uncoded RGB light fields.