5 citations · 5 across the 12 of their papers we have counts for
11 papers · 1 filter
PAGER: Partial-to-global Alignment via Geometric and Relational Distillation
Akira-Miranda Adeyomi Adeniran-Lowe, Binod Singh, Lars Arnold Dethlefsen +2
Pretrained 3D encoders are typically developed on globally reconstructed scenes expressed in a consistent world coordinate frame, whereas embodied systems must reason from partial,…
Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation
Carla Salazar, Lazaros Nalpantidis
Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity se…
AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining
Vasileios Tzouras, Paraskevas Pegios, Lazaros Nalpantidis
Field-based agricultural computer vision is important for precision agriculture, yet it largely depends on expensive annotations and costly adaptation of large pretrained models. W…
Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion
Jakub Gregorek, Paraskevas Pegios, Nando Metzger +3
We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typicall…
Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
Christoffer Koo Øhrstrøm, Rafael I. Cabral Muchacho, Yifei Dong +4
We propose Parabolic Position Encoding (PaPE), a parabola-based position encoding for vision modalities in attention-based architectures. Given a set of vision tokens-such as from…
Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
Christoffer Koo Øhrstrøm, Ronja Güldenring, Lazaros Nalpantidis
We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous and spatially sparse events, our…
ClustViT: Clustering-based Token Merging for Semantic Segmentation
Fabio Montello, Ronja Güldenring, Lazaros Nalpantidis
Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to t…
Depth Edge Alignment Loss: DEALing with Depth in Weakly Supervised Semantic Segmentation
Patrick Schmidt, Vasileios Belagiannis, Lazaros Nalpantidis
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. T…
A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
Fabio Montello, Ronja Güldenring, Simone Scardapane +1
Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neg…
From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots
Vasileios Tzouras, Lazaros Nalpantidis, Ronja Güldenring
In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appeara…
Segmentation Dataset for Reinforced Concrete Construction
Patrick Schmidt, Lazaros Nalpantidis
This paper provides a dataset of 14,805 RGB images with segmentation labels for autonomous robotic inspection of reinforced concrete defects. Baselines for the YOLOv8L-seg, DeepLab…