Related papers: AmaraSpatial-10K: A Spatially and Semantically Ali…
Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However, existing evaluation metrics for synthetic data typically calculate latent feature…
Independent indoor mobility remains a critical challenge for individuals with visual impairments, largely due to the limited capability of existing assistive systems in detecting fine-grained hazardous objects such as chairs, tables, and…
Routine and repetitive infrastructure inspections present safety, efficiency, and consistency challenges as they are performed manually, often in challenging or hazardous environments. They can also introduce subjectivity and errors into…
3D spatial reasoning is the ability to analyze and interpret the positions, orientations, and spatial relationships of objects within the 3D space. This allows models to develop a comprehensive understanding of the 3D scene, enabling their…
Large language models (LLMs) exhibit memory-intensive behavior during decoding, making it a key bottleneck in LLM inference. To accelerate decoding execution, hybrid-bonding-based 3D-DRAM has been adopted in LLM accelerators. While this…
3D semantic occupancy and flow prediction are fundamental to spatiotemporal scene understanding. This paper proposes a vision-based framework with three targeted improvements. First, we introduce an occlusion-aware adaptive lifting…
Creating 3D semantic reconstructions of environments is fundamental to many applications, especially when related to autonomous agent operation (e.g., goal-oriented navigation or object interaction and manipulation). Commonly, 3D semantic…
Recent advancements in Large Vision-Language Models (VLMs) have demonstrated exceptional semantic understanding, yet these models consistently struggle with spatial reasoning, often failing at fundamental geometric tasks such as depth…
Artificial satellites and space debris increasingly contaminate astronomical images, affecting scientific surveys and producing large volumes of streaked exposures. Manual inspection is no longer feasible at scale, and reliable detection…
In this letter, we address the problem of exploration and metric-semantic mapping of multi-floor GPS-denied indoor environments using Size Weight and Power (SWaP) constrained aerial robots. Most previous work in exploration assumes that…
Image alignment and image restoration are classical computer vision tasks. However, there is still a lack of datasets that provide enough data to train and evaluate end-to-end deep learning models. Obtaining ground-truth data for image…
Accurate far-field speech datasets are critical for tasks such as automatic speech recognition (ASR), dereverberation, speech enhancement, and source separation. However, current datasets are limited by the trade-off between acoustic…
This work presents a systematic investigation of custom convolutional neural network architectures for satellite land use classification, achieving 97.23% test accuracy on the EuroSAT dataset without reliance on pre-trained models. Through…
Aerospace embodied intelligence aims to empower unmanned aerial vehicles (UAVs) and other aerospace platforms to achieve autonomous perception, cognition, and action, as well as egocentric active interaction with humans and the environment.…
Grasping unknown objects in unstructured environments is a critical challenge for service robots, which must operate in dynamic, real-world settings such as homes, hospitals, and warehouses. Success in these environments requires both…
As vision-based robots navigate larger environments, their spatial memory grows without bound, eventually exhausting computational resources, particularly on embedded platforms (8-16GB shared memory, $<$30W) where adding hardware is not an…
As Augmented Reality (AR) technologies advance towards immersive consumer adoption, the need for rigorous Quality of Experience (QoE) assessment becomes critical. However, existing datasets often lack ecological validity, relying on…
Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this limitation stems from a critical gap:…
Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level, but also pixel-level, semantics. These features have been…
With the rapid development of electronic commerce, the way of shopping has experienced a revolutionary evolution. To fully meet customers' massive and diverse online shopping needs with quick response, the retailing AI system needs to…