arXiv subjects

Ulrich Hillenbrand

Publications and source records attributed to Ulrich Hillenbrand.

7 recordsLinked to original sources

arXiv2026

Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image

While generative models have seen significant adoption across a wide range of data modalities, including 3D data, a consensus on which model is best suited for which task has yet to be reached. Further, conditional information such as text and images to steer the generation process are frequently employed, whereas others, like partial 3D data, have not been thoroughly evaluated. In this work, we compare two of the most promising generative models--Denoising Diffusion Probabilistic Models and Autoregressive Causal Transformers--which we adapt for the tasks of generative shape modeling and completion. We conduct a thorough quantitative evaluation and comparison of both tasks, including a baseline discriminative model and an extensive ablation study. Our results show that (1) the diffusion model with continuous latents outperforms both the discriminative model and the autoregressive approach and delivers state-of-the-art performance on multi-modal shape completion from a single, noisy depth image under realistic conditions and (2) when compared on the same discrete latent space, the autoregressive model can match or exceed diffusion performance on these tasks.

cs.CV↗

arXiv2026

Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand

Grasping objects with limited or no prior knowledge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem, especially when it comes to only partial observability and versatile grasping with multi-fingered hands. We present a novel, fast, and high fidelity deep learning pipeline consisting of a shape completion module that is based on a single depth image, and followed by a grasp predictor that is based on the predicted object shape. The shape completion network is based on VQDIF and predicts spatial occupancy values at arbitrary query points. As grasp predictor, we use our two-stage architecture that first generates hand poses using an autoregressive model and then regresses finger joint configurations per pose. Critical factors turn out to be sufficient data realism and augmentation, as well as special attention to difficult cases during training. Experiments on a physical robot platform demonstrate successful grasping of a wide range of household objects based on a depth image from a single viewpoint. The whole pipeline is fast, taking only about 1 s for completing the object's shape (0.7 s) and generating 1000 grasps (0.3 s).

cs.RO↗

arXiv2026

Shape Completion with Prediction of Uncertain Regions

Shape completion, i.e., predicting the complete geometry of an object from a partial observation, is highly relevant for several downstream tasks, most notably robotic manipulation. When basing planning or prediction of real grasps on object shape reconstruction, an indication of severe geometric uncertainty is indispensable. In particular, there can be an irreducible uncertainty in extended regions about the presence of entire object parts when given ambiguous object views. To treat this important case, we propose two novel methods for predicting such uncertain regions as straightforward extensions of any method for predicting local spatial occupancy, one through postprocessing occupancy scores, the other through direct prediction of an uncertainty indicator. We compare these methods together with two known approaches to probabilistic shape completion. Moreover, we generate a dataset, derived from ShapeNet, of realistically rendered depth images of object views with ground-truth annotations for the uncertain regions. We train on this dataset and test each method in shape completion and prediction of uncertain regions for known and novel object instances and on synthetic and real data. While direct uncertainty prediction is by far the most accurate in the segmentation of uncertain regions, both novel methods outperform the two baselines in shape completion and uncertain region prediction, and avoiding the predicted uncertain regions increases the quality of grasps for all tested methods.

cs.CV↗

arXiv2002

Subthreshold dynamics of the neural membrane potential driven by stochastic synaptic input

In the cerebral cortex, neurons are subject to a continuous bombardment of synaptic inputs originating from the network's background activity. This leads to ongoing, mostly subthreshold membrane dynamics that depends on the statistics of the background activity and of the synapses made on a neuron. Subthreshold membrane polarization is, in turn, a potent modulator of neural responses. The present paper analyzes the subthreshold dynamics of the neural membrane potential driven by synaptic inputs of stationary statistics. Synaptic inputs are considered in linear interaction. The analysis identifies regimes of input statistics which give rise to stationary, fluctuating, oscillatory, and unstable dynamics. In particular, I show that (i) mere noise inputs can drive the membrane potential into sustained, quasiperiodic oscillations (noise-driven oscillations), in the absence of a stimulus-derived, intraneural, or network pacemaker; (ii) adding hyperpolarizing to depolarizing synaptic input can increase neural activity (hyperpolarization-induced activity), in the absence of hyperpolarization-activated currents.

physics.bio-ph↗

arXiv2002

Spatiotemporal adaptation through corticothalamic loops: A hypothesis

The thalamus is the major gate to the cortex and its control over cortical responses is well established. Cortical feedback to the thalamus is, in turn, the anatomically dominant input to relay cells, yet its influence on thalamic processing has been difficult to interpret. For an understanding of complex sensory processing, detailed concepts of the corticothalamic interplay need yet to be established. Drawing on various physiological and anatomical data, we elaborate the novel hypothesis that the visual cortex controls the spatiotemporal structure of cortical receptive fields via feedback to the lateral geniculate nucleus. Furthermore, we present and analyze a model of corticogeniculate loops that implements this control, and exhibit its ability of object segmentation by statistical motion analysis in the visual field.

physics.bio-ph↗

arXiv2002

Does Corticothalamic Feedback Control Cortical Velocity Tuning?

The thalamus is the major gate to the cortex and its contribution to cortical receptive field properties is well established. Cortical feedback to the thalamus is, in turn, the anatomically dominant input to relay cells, yet its influence on thalamic processing has been difficult to interpret. For an understanding of complex sensory processing, detailed concepts of the corticothalamic interplay need yet to be established. To study corticogeniculate processing in a model, we draw on various physiological and anatomical data concerning the intrinsic dynamics of geniculate relay neurons, the cortical influence on relay modes, lagged and nonlagged neurons, and the structure of visual cortical receptive fields. In extensive computer simulations we elaborate the novel hypothesis that the visual cortex controls via feedback the temporal response properties of geniculate relay cells in a way that alters the tuning of cortical cells for speed.

physics.bio-ph↗

arXiv2002

Probabilistic Search for Object Segmentation and Recognition

The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework. Object models are formulated as generative models for range data of the scene. A new statistical criterion, the truncated object probability, is introduced to infer an optimal sequence of object hypotheses to be evaluated for their match to the data. The truncated probability is partly determined by prior knowledge of the objects and partly learned from data. Some experiments on sequence quality and object segmentation and recognition from stereo data are presented. The article recovers classic concepts from object recognition (grouping, geometric hashing, alignment) from the probabilistic perspective and adds insight into the optimal ordering of object hypotheses for evaluation. Moreover, it introduces point-relation densities, a key component of the truncated probability, as statistical models of local surface shape.

cs.CV↗