arXiv subjects

André Kaup

Publications and source records attributed to André Kaup.

At least 19 recordsLinked to original sources

arXiv2026

Disparity Estimation of Planar Reflective Surfaces Using Specular Reflections From a Single Light Source

Multi-camera imaging and camera arrays have become ubiquitous in many applications, such as autonomous driving, robot control, or virtual reality, and accurate disparity maps of objects and their environment are essential for reliable operation. Despite recent advances in neural networks, correctly estimating the disparity of flat and textureless objects remains challenging. In particular, we consider a scenario defined by flat, textureless surfaces illuminated by a single fixed light source, resulting in one dominant specular reflection visible on the object surface. Under these conditions, reliable geometric and photometric cues are missing, and the specular reflection often causes mispredictions, especially when using conventional methods that rely on texture information to match corresponding pixels. To address this issue, the novel Specular Reflection Disparity Estimation SRDE algorithm is introduced, which is specifically designed for the constrained scenario of planar, textureless objects and single-source illumination. Unlike conventional stereo matching methods, SRDE ignores texture and instead leverages the geometric properties of specular reflections by incorporating the position information of the reflective region, the light source, and the camera setup. We show that SRDE outperforms existing methods by a notable margin, achieving more than a 52% improvement in End Point Error on synthetic images. Further tests demonstrate superior performance on real-world data. Furthermore, we integrate SRDE into existing neural disparity estimation pipelines by selectively replacing predictions in specular regions without modifying the backbone model. This hybrid strategy enables additional performance gains without requiring network retraining.

eess.IV↗

arXiv2026

Hierarchical Filter Band Selection for Multispectral Object Classification

Multispectral camera arrays capture image data in various spectral bands, enabling image acquisition beyond human perception. These systems are widely used in medical, agricultural, environmental, and remote sensing applications. However, not all recorded bands are needed for classification tasks, thus reducing them can lower hardware complexity and cost. The conditional filter band selection algorithm addresses this by selecting low-noise, non-redundant bands to minimize the number of filters and cameras. This paper improves the approach by introducing a second classification stage that estimates object material in addition to the object label. This information is merged by a decision-tree based band selection strategy. The proposed method achieves a 28.9% relative reduction in classification error on the SMM50 dataset compared to the state-of-the-art. Moreover, for the same classification accuracy, the required number of cameras is reduced from 7 to 4, demonstrating that the proposed approach improves performance while significantly lowering hardware requirements.

eess.IV↗

arXiv2026

Blind Stereoscopic Omnidirectional Image Quality Assessment Using Predictive Coding Hierarchy

Stereoscopic omnidirectional images (SOIs) have provided users with newly immersive quality of experience in virtual reality environments. However, developing efficient and accurate perceptual quality assessment metrics for SOIs remains challenging due to many factors such as freely changeable field of views and binocular vision. In this paper, based on the characteristics of the human visual system (HVS), we propose a Predictive Coding Hierarchy-inspired metric (PCH) for blind/no-reference stereoscopic omnidirectional image quality assessment. Motivated by the viewing process of SOIs, the proposed PCH includes a local cyclopean perception module, a global predictive perception module, and a visual quality regressor. First, observers browse different spherical sceneries from viewports, and aggregate the local visual information to infer the perceptual quality of SOIs. Therefore, we extract various viewports, followed by cyclopean conversion and saliency detection to approach the perception and attention of the human brain. After the local aggregation, viewers then infer the global scene in their minds. Based on the binocular mechanism, we fuse left and right views to perform predictive coding hierarchy modelling. Finally, the visual quality regressor is exploited to obtain the ultimate quality score related to both local and global perceptual cues. Extensive experiments demonstrate that the proposed PCH achieves competitive and consistently improved performance compared with state-of-the-art quality assessment methods.

cs.CV↗

arXiv2026

Towards Object Segmentation Mask Selection Using Specular Reflections

Specular reflections pose a significant challenge for object segmentation, as their sharp intensity transitions often mislead both conventional algorithms and deep learning based methods. However, as the specular reflection must lie on the surface of the object, this fact can be exploited to improve the segmentation masks. By identifying the largest region containing the reflection as the object, we derive a more accurate object mask without requiring specialized training data or model adaption. We evaluate our method on both synthetic and real world images and compare it against established and state-of-the-art techniques including Otsu thresholding, YOLO, and SAM2. Compared to the best performing baseline SAM2, our approach achieves up to 26.7% improvement in IoU, 22.3% in DSC, and 9.7% in pixel accuracy. Qualitative evaluations on real world images further confirm the robustness and generalizability of the proposed approach.

eess.IV↗

arXiv2026

Multispectral Household Plastic Classification for Recycling Using a Camera Array

Plastic pollution has become a persistent problem in natural ecosystems. Driven by insufficient waste management, limited recycling efficiency, and high costs for recycling, plastic waste in the environment poses significant ecological and health risks. Recycling requires accurate identification of polymer types, but existing optical sorting systems often struggle to distinguish common household plastics. In this work, we present a novel classification approach based on a multispectral imaging system consisting of nine cameras equipped with near-infrared bandpass filters. The system is designed to discriminate the seven most common household plastics. From the resulting multispectral images, we extract the spectral fingerprints and derive features such as intensity differences between specific wavelength pairs and their slopes, as well as false-color image representations. A dedicated preprocessing pipeline aligns and normalizes the data before classification. We recorded a multispectral household plastic database (https://github.com/FAU-LMS/MHPM) and trained four different classifiers Gradient Boosting, Extreme Gradient Boosting, Light Gradient Boosting Machine, and CatBoost. The best-performing model achieves a classification accuracy of 86.7%. The computational runtime is 2.603 μs per pixel, enabling efficient processing of high-resolution images. The entire setup is built from off-the-shelf hardware components, which makes replication straightforward and allows direct integration into industrial sorting pipelines.

eess.IV↗

arXiv2026

Perceptually-Weighted Video Quality Metric for Asymmetric Encoded Sports Videos

Objective video quality metrics commonly assume uniform spatial attention, an assumption that conflicts with the selective nature of human visual perception, particularly in sports videos. Here, allocating more bits for salient regions through semantic encoding can lead to significant bitrate savings. We present a Perceptually-Weighted Video Quality Metric (PW-VQM), a full-reference metric that accounts for the unequal perceptual importance of spatial regions and therefore targets quality evaluation for asymmetrically encoded content. SSIM maps computed in a multiscale wavelet domain are weighted by differentiating between foreground and background regions. Perceptually salient foreground regions are identified by combining open-vocabulary object detection with optical flow analysis, and are assigned higher weight during quality aggregation. Evaluated on sports video content, PW-VQM achieves a Spearman Rank Order Correlation Coefficient of 0.9511, outperforming established metrics including SSIM, VMAF, FUNQUE, and LPIPS. An ablation study confirms the individual contributions of the components of the perceptual weighting.

eess.IV↗

arXiv2026

Point Cloud Upsampling through Patch-based Frequency Superposition

In recent years, neural networks have become the dominant models in most point cloud upsampling methods. Although these approaches are achieving good results, they do have drawbacks, such as a lack of interpretability and data dependency. Moreover, they have to be trained on a dataset that is similar to the test data in order to perform well. To avoid these disadvantages, we propose Point Cloud Upsampling through Patch-based Frequency Superposition (PUtPFS), an optimization-based approach that selects subsets of points and estimates the surface of this set through superpositioning spatial frequencies. Then, new points are placed on this surface. By successively selecting points in the least dense regions of the point cloud, a uniform upsampling can be reached. With this method, we surpass the current best upsampling results in the commonly considered point-to-surface distance. Furthermore, we achieve the best Chamfer and Hausdorff distance among the optimization-based approaches. As an additional advantage, our method does not need any training data and is mathematically interpretable.

cs.CV↗

arXiv2026

I2PRef: Image-Driven Point Completion with Iterative Refinement

We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, with no need for 3D inputs. Additionally, we introduce a transformer-based Point-to-Point (P2P) refinement module that uses self- and cross-attention between point tokens and image features to iteratively refine the coarse I2P output. The I2P module enables the image encoder to learn rich geometric representations, while the P2P module progressively recovers fine-grained details. Unlike existing multimodal methods that rely on auxiliary losses or fusion modules, our explicit I2P task provides a strong, geometry-aware prior based on images alone. Extensive experiments on ShapeNet-ViPC demonstrate state-of-the-art completion performance with a 12.3% relative Chamfer Distance improvement over prior methods. Code is available at: https://github.com/AzharSindhi/I2PRef.git

cs.CV↗

arXiv2026

Parallel Context Modeling for Sliding Window Attention in Neural Video Coding

Most neural video codecs rely on temporal conditioning, which makes them susceptible to error propagation over long sequences. While Transformer-based architectures like the VCT offer a drift-free alternative, they suffer from high computational complexity and inferior RD performance. The recent SWA addresses these shortcomings by reducing complexity and enhancing RD performance, yet it restricts decoding to a strictly sequential raster-scan order, creating a critical bottleneck in decoding latency. To resolve this, we propose P-SWA, utilizing diagonal wavefronts to enable parallel decoding. By embedding a hyperprior and introducing an accumulator to fuse side information and local spatial context, our method increases decoding speed by 36% over the parallel VCT. Simultaneously, it achieves Bjøntegaard Delta-rate savings of up to 10.0% for I-frames and 7.1% for P-frames over the SWA baseline.

eess.IV↗

arXiv2026

TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement

Scalable compression is essential for bandwidth-adaptive transmission, yet most learned codecs are optimized for a fixed rate-distortion point, making rate adaptation costly due to re-encoding or maintaining multiple bitstreams. In this work, we propose TAFA-GSGC, a scalable learned point cloud geometry codec that enables multi-quality decoding from a single bitstream and a single trained model. TAFA-GSGC combines layered residual refinement with channel-group entropy coding, and introduces a Target-Aligned Feature Aggregation module to reduce cross-layer redundancy in enhancement residuals. Our framework supports up to 9 decodable quality levels with monotonic quality improvement as more subbitstreams are received, while maintaining strong compression efficiency. Compared with the PCGCv2 baseline, TAFA-GSGC demonstrates improved RD performance, achieving average BD-rate reductions of 4.99% and 5.92% in terms of D1-PSNR and D2-PSNR, respectively.

cs.CV↗

arXiv2026

Anti-Aliasing Snapshot HDR Imaging Using Non-Regular Sensing

Snapshot HDR imaging is essential to capture the full dynamic range of a scene in a single exposure, making it essential for video and dynamic environments where motion prevents the use of multi-exposure techniques or complex hardware set-ups. This work presents a snapshot HDR imaging sensor that is based on spatially varying apertures, implemented by combining two differently sized prototype pixels. The different light integration areas physically extend the dynamic range towards the lower end, compared to a standard high resolution sensor. A non-regular pixel arrangement is suggested, to mitigate aliasing and overcome a loss in spatial resolution that is associated with increased light integration area of the larger prototype pixel. Subsequent reconstruction in the Fourier domain, where natural images can be sparsely represented allows to recover the image with high detail. The image acquisition approach with the proposed non-regular HDR sensor is simulated and analysed with special emphasis on the spatial resolution. The results suggest the snapshot HDR sensor layout to be an effective way to acquire images with high dynamic range and free from aliasing artefacts.

eess.IV↗

arXiv2026

Domain Adaptation for Camera-Specific Image Characteristics using Shallow Discriminators

Each image acquisition setup leads to its own camera-specific image characteristics degrading the image quality. In learning-based perception algorithms, characteristics occurring during the application phase, but absent in the training data, lead to a domain gap impeding the performance. Previously, pixel-level domain adaptation through unpaired learning of the pristine-to-distorted mapping function has been proposed. In this work, we propose shallow discriminator architectures to address limitations of these approaches. We show that a smaller receptive field size improves learning of unknown image distortions by more accurately reproducing local distortion characteristics at a low network complexity. In a domain adaptation setup for instance segmentation, we achieve mean average precision increases over previous methods of up to 0.15 for individual distortions and up to 0.16 for camera-specific image characteristics in a simplified camera model. In terms of number of parameters, our approach matches the complexity of one state of the art method while reducing complexity by a factor of 20 compared to another, demonstrating superior efficiency without compromising performance.

eess.IV↗

arXiv2026

LRC-DHVC: Towards Local Rate Control in Neural Video Compression

Local rate control is a key enabler to generalize image and video compression for dedicated challenges, such as video coding for machines. While traditional hybrid video coding can easily adapt the local rate-distortion trade-off by changing the local quantization parameter, no such approach is currently available for learning-based video compression. In this paper, we propose LRC-DHVC, a hierarchical video compression network, which allows continuous local rate control on a pixel level to vary the spatial quality distribution within individual video frames. This is achieved by concatenating a quality map to the input frame and applying a weighted MSE loss which matches the pixelwise trade-off factors in the quality map. During training, the model sees a variety of quality maps due to a constrained-random generation. Our model is the first neural video compression network, which can continuously and spatially adapt to varying quality constraints. Due to the wide quality and bit rate range, a single set of network parameters is sufficient. Compared to single rate point networks, which scale linearly with the number of rate points, the memory requirements for our network parameters remain constant. The code and model are available at link-updated-upon-acceptance.

eess.IV↗

arXiv2025

Visual Autoregressive Modelling for Monocular Depth Estimation

We propose a monocular depth estimation method based on visual autoregressive (VAR) priors, offering an alternative to diffusion-based approaches. Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism with classifier-free guidance. Our approach performs inference in ten fixed autoregressive stages, requiring only 74K synthetic samples for fine-tuning, and achieves competitive results. We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets. This work establishes autoregressive priors as a complementary family of geometry-aware generative models for depth estimation, highlighting advantages in data scalability, and adaptability to 3D vision tasks. Code available at "https://github.com/AmirMaEl/VAR-Depth".

cs.CV↗

arXiv2025

TreeNet: A Light Weight Model for Low Bitrate Image Compression

Reducing computational complexity remains a critical challenge for the widespread adoption of learning-based image compression techniques. In this work, we propose TreeNet, a novel low-complexity image compression model that leverages a binary tree-structured encoder-decoder architecture to achieve efficient representation and reconstruction. We employ attentional feature fusion mechanism to effectively integrate features from multiple branches. We evaluate TreeNet on three widely used benchmark datasets and compare its performance against competing methods including JPEG AI, a recent standard in learning-based image compression. At low bitrates, TreeNet achieves an average improvement of 4.83% in BD-rate over JPEG AI, while reducing model complexity by 87.82%. Furthermore, we conduct extensive ablation studies to investigate the influence of various latent representations within TreeNet, offering deeper insights into the factors contributing to reconstruction.

cs.CV↗

arXiv2025

A High-Level Feature Model to Predict the Encoding Energy of a Hardware Video Encoder

In today's society, live video streaming and user generated content streamed from battery powered devices are ubiquitous. Live streaming requires real-time video encoding, and hardware video encoders are well suited for such an encoding task. In this paper, we introduce a high-level feature model using Gaussian process regression that can predict the encoding energy of a hardware video encoder. In an evaluation setup restricted to only P-frames and a single keyframe, the model can predict the encoding energy with a mean absolute percentage error of approximately 9%. Further, we demonstrate with an ablation study that spatial resolution is a key high-level feature for encoding energy prediction of a hardware encoder. A practical application of our model is that it can be used to perform a prior estimation of the energy required to encode a video at various spatial resolutions, with different coding standards and codec presets.

eess.IV↗

arXiv2025

Sliding Window Attention for Learned Video Compression

To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive fields. When adapted for temporal autoregressive models, this paradigm, exemplified by the Video Compression Transformer (VCT), also necessitates computationally redundant overlapping windows. This work introduces 3D Sliding Window Attention (SWA), a patchless form of local attention. By enabling a decoder-only architecture that unifies spatial and temporal context processing, and by providing a uniform receptive field, our method significantly improves rate-distortion performance, achieving Bjørntegaard Delta-rate savings of up to 18.6 % against the VCT baseline. Simultaneously, by eliminating the need for overlapping windows, our method reduces overall decoder complexity by a factor of 2.8, while its entropy model is nearly 3.5 times more efficient. We further analyze our model's behavior and show that while it benefits from long-range temporal context, excessive context can degrade performance.

eess.IV↗

arXiv2025

Optimized Learned Image Compression for Facial Expression Recognition

Efficient data compression is crucial for the storage and transmission of visual data. However, in facial expression recognition (FER) tasks, lossy compression often leads to feature degradation and reduced accuracy. To address these challenges, this study proposes an end-to-end model designed to preserve critical features and enhance both compression and recognition performance. A custom loss function is introduced to optimize the model, tailored to balance compression and recognition performance effectively. This study also examines the influence of varying loss term weights on this balance. Experimental results indicate that fine-tuning the compression model alone improves classification accuracy by 0.71% and compression efficiency by 49.32%, while joint optimization achieves significant gains of 4.04% in accuracy and 89.12% in efficiency. Moreover, the findings demonstrate that the jointly optimized classification model maintains high accuracy on both compressed and uncompressed data, while the compression model reliably preserves image details, even at high compression rates.

cs.CV↗