Search

In this paper, we present a novel architecture for interactive segmentation in winter sports contexts. The field of interactive segmentation deals with the prediction of high-quality segmentation masks by informing the network about the objects position with the help of user guidance. In our case the guidance consists of click prompts. For this task, we first present a baseline architecture which is specifically geared towards quickly responding after each click. Afterwards, we motivate and describe a number of architectural modifications which improve the performance when tasked with segmenting winter sports equipment on the WSESeg dataset. With regards to the average NoC@85 metric on the WSESeg classes, we outperform SAM and HQ-SAM by 2.336 and 7.946 clicks, respectively. When applied to the HQSeg-44k dataset, our system delivers state-of-the-art results with a NoC@90 of 6.00 and NoC@95 of 9.89. In addition to that, we test our model on a novel dataset containing masks for humans during skiing., Comment: 4 figures, 6 tables, 12 pages

In this paper, we draw an analogy between processing natural languages and processing multivariate event streams from vehicles in order to predict $\textit{when}$ and $\textit{what}$ error pattern is most likely to occur in the future for a given car. Our approach leverages the temporal dynamics and contextual relationships of our event data from a fleet of cars. Event data is composed of discrete values of error codes as well as continuous values such as time and mileage. Modelled by two causal Transformers, we can anticipate vehicle failures and malfunctions before they happen. Thus, we introduce $\textit{CarFormer}$, a Transformer model trained via a new self-supervised learning strategy, and $\textit{EPredictor}$, an autoregressive Transformer decoder model capable of predicting $\textit{when}$ and $\textit{what}$ error pattern will most likely occur after some error code apparition. Despite the challenges of high cardinality of event types, their unbalanced frequency of appearance and limited labelled data, our experimental results demonstrate the excellent predictive ability of our novel model. Specifically, with sequences of $160$ error codes on average, our model is able with only half of the error codes to achieve $80\%$ F1 score for predicting $\textit{what}$ error pattern will occur and achieves an average absolute error of $58.4 \pm 13.2$h $\textit{when}$ forecasting the time of occurrence, thus enabling confident predictive maintenance and enhancing vehicle safety., Comment: 10 pages, 8 figures, accepted to AAAI 2025

The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes.

In this paper we introduce a new dataset containing instance segmentation masks for ten different categories of winter sports equipment, called WSESeg (Winter Sports Equipment Segmentation). Furthermore, we carry out interactive segmentation experiments on said dataset to explore possibilities for efficient further labeling. The SAM and HQ-SAM models are conceptualized as foundation models for performing user guided segmentation. In order to measure their claimed generalization capability we evaluate them on WSESeg. Since interactive segmentation offers the benefit of creating easily exploitable ground truth data during test-time, we are going to test various online adaptation methods for the purpose of exploring potentials for improvements without having to fine-tune the models explicitly. Our experiments show that our adaptation methods drastically reduce the Failure Rate (FR) and Number of Clicks (NoC) metrics, which generally leads faster to better interactive segmentation results., Comment: 7 pages, 1 figure, 3 tables, Accepted at CBMI 2024

In panoptic scene graph generation (PSGG), models retrieve interactions between objects in an image which are grounded by panoptic segmentation masks. Previous evaluations on panoptic scene graphs have been subject to an erroneous evaluation protocol where multiple masks for the same object can lead to multiple relation distributions per mask-mask pair. This can be exploited to increase the final score. We correct this flaw and provide a fair ranking over a wide range of existing PSGG models. The observed scores for existing methods increase by up to 7.4 mR@50 for all two-stage methods, while dropping by up to 19.3 mR@50 for all one-stage methods, highlighting the importance of a correct evaluation. Contrary to recent publications, we show that existing two-stage methods are competitive to one-stage methods. Building on this, we introduce the Decoupled SceneFormer (DSFormer), a novel two-stage model that outperforms all existing scene graph models by a large margin of +11 mR@50 and +10 mNgR@50 on the corrected evaluation, thus setting a new SOTA. As a core design principle, DSFormer encodes subject and object masks directly into feature space.

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number of tokens through token merging, which has exhibited remarkable enhancements in inference speed, training efficiency, and memory utilization for image classification tasks. In this paper, we explore various token merging strategies within the framework of the Segformer architecture and perform experiments on multiple semantic segmentation and human pose estimation datasets. Notably, without model re-training, we, for example, achieve an inference acceleration of 61% on the Cityscapes dataset while maintaining the mIoU performance. Consequently, this paper facilitates the deployment of transformer-based architectures on resource-constrained devices and in real-time applications., Comment: 7 pages, to be published in IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2024

Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years. However, despite these strides, precise and thorough definitions for the metrics used to evaluate scene graph generation models are lacking. In this paper, we address this gap in the literature by providing a review and precise definition of commonly used metrics in scene graph generation. Our comprehensive examination clarifies the underlying principles of these metrics and can serve as a reference or introduction to scene graph metrics. Furthermore, to facilitate the usage of these metrics, we introduce a standalone Python package called SGBench that efficiently implements all defined metrics, ensuring their accessibility to the research community. Additionally, we present a scene graph benchmarking web service, that enables researchers to compare scene graph generation methods and increase visibility of new methods in a central place. All of our code can be found at https://lorjul.github.io/sgbench/.

The interactive segmentation task consists in the creation of object segmentation masks based on user interactions. The most common way to guide a model towards producing a correct segmentation consists in clicks on the object and background. The recently published Segment Anything Model (SAM) supports a generalized version of the interactive segmentation problem and has been trained on an object segmentation dataset which contains 1.1B masks. Though being trained extensively and with the explicit purpose of serving as a foundation model, we show significant limitations of SAM when being applied for interactive segmentation on novel domains or object types. On the used datasets, SAM displays a failure rate $\text{FR}_{30}@90$ of up to $72.6 \%$. Since we still want such foundation models to be immediately applicable, we present a framework that can adapt SAM during immediate usage. For this we will leverage the user interactions and masks, which are constructed during the interactive segmentation process. We use this information to generate pseudo-labels, which we use to compute a loss function and optimize a part of the SAM model. The presented method causes a relative reduction of up to $48.1 \%$ in the $\text{FR}_{20}@85$ and $46.6 \%$ in the $\text{FR}_{30}@90$ metrics., Comment: 11 pages, 2 figures, 4 tables

We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels. No expensive 3D labels are needed. Thus, instead of using 3D labels, our model is trained with easy-to-annotate 2D labels along with the physical knowledge of the object's motion. Given this information, the model can infer the latent third dimension, even though it has never seen this information during training. Our method is evaluated on both synthetic and real-world datasets, and we are able to achieve a mean distance error of just 6 cm in our experiments on real data. The results indicate the method's potential as a step towards learning 3D object location estimation, where collecting 3D data for training is not feasible.

Current scene graph datasets suffer from strong long-tail distributions of their predicate classes. Due to a very low number of some predicate classes in the test sets, no reliable metrics can be retrieved for the rarest classes. We construct a new panoptic scene graph dataset and a set of metrics that are designed as a benchmark for the predictive performance especially on rare predicate classes. To construct the new dataset, we propose a model-assisted annotation pipeline that efficiently finds rare predicate classes that are hidden in a large set of images like needles in a haystack. Contrary to prior scene graph datasets, Haystack contains explicit negative annotations, i.e. annotations that a given relation does not have a certain predicate class. Negative annotations are helpful especially in the field of scene graph generation and open up a whole new set of possibilities to improve current scene graph generation models. Haystack is 100% compatible with existing panoptic scene graph datasets and can easily be integrated with existing evaluation pipelines. Our dataset and code can be found here: https://lorjul.github.io/haystack/. It includes annotation files and simple to use scripts and utilities, to help with integrating our dataset in existing work.

Electrically controllable quantum-dot molecules (QDMs) are a promising platform for deterministic entanglement generation and, as such, a resource for quantum-repeater networks. We develop a microscopic open-quantum-systems approach based on a time-dependent Bloch-Redfield equation to model the generation of entangled spin states with high fidelity. The state preparation is a crucial step in a protocol for deterministic entangled-photon-pair generation that we propose for quantum repeater applications. Our theory takes into account the quantum-dot molecules' electronic properties that are controlled by time-dependent electric fields as well as dissipation due to electron-phonon interaction. We quantify the transition between adiabatic and non-adiabatic regimes, which provides insights into the dynamics of adiabatic control of QDM charge states in the presence of dissipative processes. From this, we infer the maximum speed of entangled-state preparation under different experimental conditions, which serves as a first step towards simulation of attainable entangled photon-pair generation rates. The developed formalism opens the possibility for device-realistic descriptions of repeater protocol implementations., Comment: 12 pages, 11 figures

Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains absent. This study implements the Type Three (T3) challenge format, which allows for training solutions on private data and guarantees reusable training methodologies. With T3, challenge organizers train a codebase provided by the participants on sequestered training data. T3 was implemented in the STOIC2021 challenge, with the goal of predicting from a computed tomography (CT) scan whether subjects had a severe COVID-19 infection, defined as intubation or death within one month. STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects. The organizers successfully trained six of the eight Final phase submissions. The submitted codebases for training and running inference were released publicly. The winning solution obtained an area under the receiver operating characteristic curve for discerning between severe and non-severe COVID-19 of 0.815. The Final phase solutions of all finalists improved upon their Qualification phase solutions.HSUXJM-TNZF9CHSUXJM-TNZF9C

Pseudo depth maps are depth map predicitions which are used as ground truth during training. In this paper we leverage pseudo depth maps in order to segment objects of classes that have never been seen during training. This renders our object segmentation task an open world task. The pseudo depth maps are generated using pretrained networks, which have either been trained with the full intention to generalize to downstream tasks (LeRes and MiDaS), or which have been trained in an unsupervised fashion on video sequences (MonodepthV2). In order to tell our network which object to segment, we provide the network with a single click on the object's surface on the pseudo depth map of the image as input. We test our approach on two different scenarios: One without the RGB image and one where the RGB image is part of the input. Our results demonstrate a considerably better generalization performance from seen to unseen object types when depth is used. On the Semantic Boundaries Dataset we achieve an improvement from $61.57$ to $69.79$ IoU score on unseen classes, when only using half of the training classes during training and performing the segmentation on depth maps only., Comment: Accepted to L3D-IVU Workshop at CVPR 2023

Performance analyses based on videos are commonly used by coaches of athletes in various sports disciplines. In individual sports, these analyses mainly comprise the body posture. This paper focuses on the disciplines of triple, high, and long jump, which require fine-grained locations of the athlete's body. Typical human pose estimation datasets provide only a very limited set of keypoints, which is not sufficient in this case. Therefore, we propose a method to detect arbitrary keypoints on the whole body of the athlete by leveraging the limited set of annotated keypoints and auto-generated segmentation masks of body parts. Evaluations show that our model is capable of detecting keypoints on the head, torso, hands, feet, arms, and legs, including also bent elbows and knees. We analyze and compare different techniques to encode desired keypoints as the model's input and their embedding for the Transformer backbone., Comment: Accepted at CVSports23 (Workshop at CVPR 23)

Self-assembled optically active quantum dot molecules (QDMs) allow the creation of protected qubits via singlet-triplet spin states. The qubit energy splitting of these states is defined by the tunnel coupling strength and is, therefore, determined by the potential landscape and thus fixed during growth. Applying an in-plane magnetic field increases the confinement of the hybridized wave functions within the quantum dots, leading to a decrease of the tunnel coupling strength. We achieve a tuning of the coupling strength by $(53.4\pm1.7)$ %. The ability to fine-tune this coupling is essential for quantum network and computing applications that require quantum systems with near identical performance., Comment: Main: 6 pages, 3 figures, Supplemental: 4 pages, 2 figures

We report on scalable heterointegration of superconducting electrodes and epitaxial semiconductor quantum dots on strong piezoelectric and optically nonlinear lithium niobate. The implemented processes combine the sputter-deposited thin film superconductor niobium nitride and III-V compound semiconductor membranes onto the host substrate. The superconducting thin film is employed as a zero-resistivity electrode material for a surface acoustic wave resonator with internal quality factors $Q \approx 17000$ representing a three-fold enhancement compared to identical devices with normal conducting electrodes. Superconducting operation of $\approx 400\,\mathrm{MHz}$ resonators is achieved to temperatures $T>7\,\mathrm{K}$ and electrical radio frequency powers $P_{\mathrm{rf}}>+9\,\mathrm{dBm}$. Heterogeneously integrated single quantum dots couple to the resonant phononic field of the surface acoustic wave resonator operated in the superconducting regime. Position and frequency selective coupling mediated by deformation potential coupling is validated using time-integrated and time-resolved optical spectroscopy. Furthermore, acoustoelectric charge state control is achieved in a modified device geometry harnessing large piezoelectric fields inside the resonator. The hybrid quantum dot - surface acoustic wave resonator can be scaled to higher operation frequencies and smaller mode volumes for quantum phase modulation and transduction between photons and phonons via the quantum dot. Finally, the employed materials allow for the realization of other types of optoelectronic devices, including superconducting single photon detectors and integrated photonic and phononic circuits., Comment: submitted manuscript

Quantum dot molecules (QDMs) are one of the few quantum light sources that promise deterministic generation of one- and two-dimensional photonic graph states. The proposed protocols rely on coherent excitation of the tunnel-coupled and spatially indirect exciton states. Here, we demonstrate power-dependent Rabi oscillations of direct excitons, spatially indirect excitons, and excitons with a hybridized electron wave function. An off-resonant detection technique based on phonon-mediated state transfer allows for spectrally filtered detection under resonant excitation. Applying a gate voltage to the QDM-device enables a continuous transition between direct and indirect excitons and, thereby, control of the overlap of the electron and hole wave function. This does not only vary the Rabi frequency of the investigated transition by a factor of $\approx3$, but also allows to optimize graph state generation in terms of optical pulse power and reduction of radiative lifetimes., Comment: 6 pages, 3 figures

Analyses based on the body posture are crucial for top-class athletes in many sports disciplines. If at all, coaches label only the most important keypoints, since manual annotations are very costly. This paper proposes a method to detect arbitrary keypoints on the limbs and skis of professional ski jumpers that requires a few, only partly correct segmentation masks during training. Our model is based on the Vision Transformer architecture with a special design for the input tokens to query for the desired keypoints. Since we use segmentation masks only to generate ground truth labels for the freely selectable keypoints, partly correct segmentation masks are sufficient for our training procedure. Hence, there is no need for costly hand-annotated segmentation masks. We analyze different training techniques for freely selected and standard keypoints, including pseudo labels, and show in our experiments that only a few partly correct segmentation masks are sufficient for learning to detect arbitrary keypoints on limbs and skis., Comment: accepted at CV4WS2023 (WACV 2023 Workshops)

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and time-consuming. Current SSL approaches use an initially supervised trained model to generate predictions for unlabelled images, called pseudo-labels, which are subsequently used for training a new model from scratch. Since the predictions usually do not come from an error-free neural network, they are naturally full of errors. However, training with partially incorrect labels often reduce the final model performance. Thus, it is crucial to manage errors/noise of pseudo-labels wisely. In this work, we use three mechanisms to control pseudo-label noise and errors: (1) We construct a solid base framework by mixing images with cow-patterns on unlabelled images to reduce the negative impact of wrong pseudo-labels. Nevertheless, wrong pseudo-labels still have a negative impact on the performance. Therefore, (2) we propose a simple and effective loss weighting scheme for pseudo-labels defined by the feedback of the model trained on these pseudo-labels. This allows us to soft-weight the pseudo-label training examples based on their determined confidence score during training. (3) We also study the common practice to ignore pseudo-labels with low confidence and empirically analyse the influence and effect of pseudo-labels with different confidence ranges on SSL and the contribution of pseudo-label filtering to the achievable performance gains. We show that our method performs superior to state of-the-art alternatives on various datasets. Furthermore, we show that our findings also transfer to other tasks such as human pose estimation. Our code is available at https://github.com/ChristmasFan/SSL_Denoising_Segmentation., Comment: Accepted to BMVC 2022

The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather efficient, the true computational complexity depends on the per-frame 2D pose estimation. In this paper, we present a Transformer-based pose uplifting scheme that can operate on temporally sparse 2D pose sequences but still produce temporally dense 3D pose estimates. We show how masked token modeling can be utilized for temporal upsampling within Transformer blocks. This allows to decouple the sampling rate of input 2D poses and the target frame rate of the video and drastically decreases the total computational complexity. Additionally, we explore the option of pre-training on large motion capture archives, which has been largely neglected so far. We evaluate our method on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP. With an MPJPE of 45.0 mm and 46.9 mm, respectively, our proposed method can compete with the state-of-the-art while reducing inference time by a factor of 12. This enables real-time throughput with variable consumer hardware in stationary and mobile applications. We release our code and models at https://github.com/goldbricklemon/uplift-upsample-3dhpe, Comment: Accepted at IEEE/CVF WACV 2023

Since COVID strongly affects the respiratory system, lung CT-scans can be used for the analysis of a patients health. We introduce a neural network for the prediction of the severity of lung damage and the detection of a COVID-infection using three-dimensional CT-data. Therefore, we adapt the recent ConvNeXt model to process three-dimensional data. Furthermore, we design and analyze different pretraining methods specifically designed to improve the models ability to handle three-dimensional CT-data. We rank 2nd in the 1st COVID19 Severity Detection Challenge and 3rd in the 2nd COVID19 Detection Challenge., Comment: 17 pages, 3 figures, informations about challenge submission

Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints. Standard HPE models trained on such datasets can only detect these keypoints. If more points are desired, they have to be manually annotated and the model needs to be retrained. Our approach leverages the Vision Transformer architecture to extend the capability of the model to detect arbitrary keypoints on the limbs of persons. We propose two different approaches to encode the desired keypoints. (1) Each keypoint is defined by its position along the line between the two enclosing keypoints from the fixed set and its relative distance between this line and the edge of the limb. (2) Keypoints are defined as coordinates on a norm pose. Both approaches are based on the TokenPose architecture, while the keypoint tokens that correspond to the fixed keypoints are replaced with our novel module. Experiments show that our approaches achieve similar results to TokenPose on the fixed keypoints and are capable of detecting arbitrary keypoints on the limbs., Comment: accepted at CVSports (CVPR 2022 Workshops)

The Multimedia and Computer Vision Lab of the University of Augsburg participated in the VTT task only. We use the VATEX and TRECVID-VTT datasets for training our VTT models. We base our model on the Transformer approach for both of our submitted runs. For our second model, we adapt the X-Linear Attention Networks for Image Captioning which does not yield the desired bump in scores. For both models, we train on the complete VATEX dataset and 90% of the TRECVID-VTT dataset for pretraining while using the remaining 10% for validation. We finetune both models with self-critical sequence training, which boosts the validation performance significantly. Overall, we find that training a Video-to-Text system on traditional Image Captioning pipelines delivers very poor performance. When switching to a Transformer-based architecture our results greatly improve and the generated captions match better with the corresponding video., Comment: TRECVID 2021 notebook paper

Video-to-Text (VTT) is the task of automatically generating descriptions for short audio-visual video clips, which can support visually impaired people to understand scenes of a YouTube video for instance. Transformer architectures have shown great performance in both machine translation and image captioning, lacking a straightforward and reproducible application for VTT. However, there is no comprehensive study on different strategies and advice for video description generation including exploiting the accompanying audio with fully self-attentive networks. Thus, we explore promising approaches from image captioning and video processing and apply them to VTT by developing a straightforward Transformer architecture. Additionally, we present a novel way of synchronizing audio and video features in Transformers which we call Fractional Positional Encoding (FPE). We run multiple experiments on the VATEX dataset to determine a configuration applicable to unseen datasets that helps describe short video clips in natural language and improved the CIDEr and BLEU-4 scores by 37.13 and 12.83 points compared to a vanilla Transformer network and achieve state-of-the-art results on the MSR-VTT and MSVD datasets. Also, FPE helps increase the CIDEr score by a relative factor of 8.6%.

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation. We propose a semantically consistent image-to-image translation method in combination with a consistency regularisation method for UDA. We overcome previous limitations on transferring synthetic images to real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation model that receives additional feedback from semantic labels on both domains. Our method outperforms state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant domain adaptation benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.

Quantum technologies that rely on photonic qubits require a precise controllability of their properties. For this purpose hybrid approaches are particularly attractive because they offer a large flexibility to address different aspects of the photonic degrees of freedom. When combining photonics with other quantum platforms like phonons, quantum transducers have to be realized that convert between the mechanical and optical domain. Here, we realize this interface between phonons in the form of surface acoustic waves (SAWs) and single photons, mediated by a single semiconductor quantum dot exciton. In this combined theoretical and experimental study, we show that the different sidebands exhibit characteristic blinking dynamics that can be controlled by detuning the laser from the exciton transition. By developing analytical approximations we gain a better understanding of the involved internal dynamics. Our specific SAW approach allows us to reach the ideal frequency range of around 1 GHz that enables simultaneous temporal and spectral phonon sideband resolution close to the combined fundamental time-bandwidth limit.

Portraying emotion and trustworthiness is known to increase the appeal of video content. However, the causal relationship between these signals and online user engagement is not well understood. This limited understanding is partly due to a scarcity in emotionally annotated data and the varied modalities which express user engagement online. In this contribution, we utilise a large dataset of YouTube review videos which includes ca. 600 hours of dimensional arousal, valence and trustworthiness annotations. We investigate features extracted from these signals against various user engagement indicators including views, like/dislike ratio, as well as the sentiment of comments. In doing so, we identify the positive and negative influences which single features have, as well as interpretable patterns in each dimension which relate to user engagement. Our results demonstrate that smaller boundary ranges and fluctuations for arousal lead to an increase in user engagement. Furthermore, the extracted time-series features reveal significant (p<0.05) correlations for each dimension, such as, count below signal mean (arousal), number of peaks (valence), and absolute energy (trustworthiness). From this, an effective combination of features is outlined for approaches aiming to automatically predict several user engagement indicators. In a user engagement prediction paradigm we compare all features against semi-automatic (cross-task), and automatic (task-specific) feature selection methods. These selected feature sets appear to outperform the usage of all features, e.g., using all features achieves 1.55 likes per day (Lp/d) mean absolute error from valence; this improves through semi-automatic and automatic selection to 1.33 and 1.23 Lp/d, respectively (data mean 9.72 Lp/d with a std. 28.75 Lp/d).

The current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods. These allow 2D labels to be used to learn effective 3D human pose recovery either directly from images or via 2D-to-3D pose uplifting. In this paper we present a detailed analysis of the most commonly used simplified projection models, which relate the estimated 3D pose representation to 2D labels: normalized perspective and weak perspective projections. Specifically, we derive theoretical lower bound errors for those projection models under the commonly used mean per-joint position error (MPJPE). Additionally, we show how the normalized perspective projection can be replaced to avoid this guaranteed minimal error. We evaluate the derived lower bounds on the most commonly used 3D human pose estimation benchmark datasets. Our results show that both projection models lead to an inherent minimal error between 19.3mm and 54.7mm, even after alignment in position and scale. This is a considerable share when comparing with recent state-of-the-art results. Our paper thus establishes a theoretical baseline that shows the importance of suitable projection models in weakly supervised 3D human pose estimation., Comment: Accepted at 3DV 2020