https://fordatis.fraunhofer.de/handle/fordatis/7 Fri, 04 Sep 2026 16:53:07 GMT 2026-09-04T16:53:07Z https://fordatis.fraunhofer.de/handle/fordatis/514 Titel: Learning Motion-Aware Representations for World-Space Speed Estimation from Consecutive Frames Datenautorinnen und Datenautoren: Lintao, Fang Zusammenfassung: Object speed estimation is fundamental for understanding dynamic scenes, from traffic monitoring to animal behavior analysis. Existing monocular RGB video approaches typically rely on scene-specific information, such as camera calibration parameters or depth maps, which is often unavailable or unreliable in real-world applications. Further, speed estimation is often decomposed into separate learning problems, such as detection, tracking, depth estimation, geometric projection, and final speed regression, causing errors to accumulate across stages. We therefore propose the Motion-aware Speed Estimation Network (MotiSpeed), a lightweight end-to-end framework that replaces this multi-stage formulation with a single learned model and estimates object-level world-space speed directly from consecutive monocular RGB frames. Evaluating such models, however, requires benchmarks beyond structured planar motion. Existing speed estimation datasets are predominantly vehicle-centric, whereas datasets for unconstrained 3D motion remain limited. Therefore, we introduce AquaSpeed3D, a synthetic underwater dataset for speed estimation with freely moving agents, non-rigid appearance, occlusion, and dense multi-agent interactions. Experiments on AquaSpeed3D, 3DZeF20, and VS13 demonstrate that MotiSpeed achieves competitive performance across underwater and vehicle scenarios while remaining parameter-efficient. Thu, 26 Nov 2026 00:00:00 GMT https://fordatis.fraunhofer.de/handle/fordatis/514 2026-11-26T00:00:00Z https://fordatis.fraunhofer.de/handle/fordatis/506 Titel: Wheat3DIS: A Benchmark for 3D Instance Segmentation of Wheat Heads from Point Clouds. Datenautorinnen und Datenautoren: Singh, Ashutosh; Hoppe, Sarah; Wree, Philipp Zusammenfassung: 3D computer vision offers powerful tools for efficient agricultural analysis by enabling automated extraction of quantitative traits using point clouds of field scenes. In the context of wheat, accurate analyses of yield-related traits such as spike count, plant density and canopy structure at plot-level and organ morphology such as length, width and volume of wheat heads are essential for high throughput phenotyping. Although recent advances in 3D imaging and point-cloud learning have enabled more detailed analysis of plant architecture, the development of robust wheat phenotyping methods remains limited by the lack of annotated 3D datasets for instance-level segmentation. Existing wheat point-cloud resources primarily focus on part-level or semantic segmentation, where points are assigned to broad categories such as wheat heads, leaves and stems. However, study and analysis of wheat head morphology requires instance-level annotations. In this work, we introduce Wheat3DIS, a multi-source benchmark for 3D wheat head instance segmentation. The benchmark combines in-field wheat point clouds from various sources such as a laser-scanner, a camera array and an iphone. The benchmark provides diverse 3D representations across acquisition modalities, point densities, and reconstruction characteristics. Each scene is annotated with instance-level labels for wheat heads to support the evaluation of wheat organ separation, spike counting, and structure-aware trait extraction. Wheat3DIS provides standardized data splits, annotation protocols, evaluation metrics, and baseline results for representative 3D segmentation architectures. By focusing specifically on wheat and by moving beyond part segmentation toward instance-level understanding, Wheat3DIS establishes a reproducible benchmark for studying 3D wheat perception, cross-sensor generalization, and robust phenotyping under realistic geometric complexity. Thu, 01 Jan 2026 00:00:00 GMT https://fordatis.fraunhofer.de/handle/fordatis/506 2026-01-01T00:00:00Z https://fordatis.fraunhofer.de/handle/fordatis/500 Titel: WheatFormer3D: Segmentation and Phenotyping of Wheat Heads with Transformers Datenautorinnen und Datenautoren: Singh, Ashutosh Zusammenfassung: 3D Computer vision offers powerful tools for efficient agricultural analysis by enabling automated extraction of quantitative traits using point clouds of field scenes. In the context of wheat, accurate analysis of wheat head morphology is challenging because the acquisition of high resolution point clouds is difficult and annotating them for instance segmentation requires substantial manual effort. While 3D instance segmentation has shown promise for such tasks by explicitly modeling geometric structure, existing approaches often use simulated data or data obtained in highly controlled indoor setups. As a result, they struggle to achieve reliable instance coverage in real field conditions. In this work, we study 3D instance segmentation of wheat heads in real in-field point clouds and introduce WheatFormer3D, a transformer-based framework designed to improve query coverage of individual wheat heads in crowded scenes. We further propose domain-specific geometric augmentations that increase data efficiency and robustness in data-scarce agricultural settings. Extensive experiments demonstrate that the proposed approach consistently outperforms recent transformer-based baselines, including OneFormer3D and Mask3D, on wheat head instance segmentation, achieving 87.96 AP@50 and 77.99 AP overall. In addition, we investigate the use of segmentation outputs for downstream phenotyping tasks and construct a reference organ-level dataset with paired indoor and in-field wheat head scans and reference volume measurements. Using this dataset, we explore the feasibility and current limitations of learning-based volume estimation from real-world point clouds, highlighting challenges associated with noisy in-field reconstructions. Thu, 01 Jan 2026 00:00:00 GMT https://fordatis.fraunhofer.de/handle/fordatis/500 2026-01-01T00:00:00Z https://fordatis.fraunhofer.de/handle/fordatis/492 Titel: ConJEB: A Large Elastic Contact Jet Engine Bracket Quadratic Program Dataset Datenautorinnen und Datenautoren: Ferreira, Stephanie; Giebel, Andreas; Mueller-Roemer, Johannes Zusammenfassung: This dataset contains large-scale, sparse quadratic programs (QPs) derived from physically-based animation scenarios with contact interactions. It extends the SimJEB dataset (Wahlen et al. 2021) by introducing explicit contact handling: the abstract contact force in the original GE Jet Engine Bracket Challenge model is replaced with a detailed cylinder mesh pin. This modification yields realistic large-scale sparse QPs with hundreds of thousands to millions of degrees of freedom. The dataset is designed to enable fair, reproducible benchmarking and evaluation of QP solvers in computer graphics and related fields. Wed, 01 Apr 2026 00:00:00 GMT https://fordatis.fraunhofer.de/handle/fordatis/492 2026-04-01T00:00:00Z