相关论文: A Concise Tiling Strategy for Preserving Spatial C…

Learning robust visuomotor policies for robotic manipulation remains a challenge in real-world settings, where visual distractors can significantly degrade performance and safety. In this work, we propose an effective and scalable…

Minimizing inconsistencies across successive versions of an AI system is as crucial as reducing the overall error. In image classification, such inconsistencies manifest as negative flips, where an updated model misclassifies test samples…

Robots benefit from high-fidelity reconstructions of their environment, which should be geometrically accurate and photorealistic to support downstream tasks. While this can be achieved by building distance fields from range sensors and…

Deep learning on climatic data holds potential for macroecological applications. However, its adoption remains limited among scientists outside the deep learning community due to storage, compute, and technical expertise barriers. To…

Reconstructing intricate, ever-changing environments remains a central ambition in computer vision, yet existing solutions often crumble before the complexity of real-world dynamics. We present DynaSplat, an approach that extends Gaussian…

Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to…

Occupancy prediction provides critical geometric and semantic understanding for robotics but faces efficiency-accuracy trade-offs. Current dense methods suffer computational waste on empty voxels, while sparse query-based approaches lack…

With the advent of Neural Radiance Field (NeRF), representing 3D scenes through multiple observations has shown remarkable improvements in performance. Since this cutting-edge technique is able to obtain high-resolution renderings by…

Neural implicit representations have had a significant impact on simultaneous localization and mapping (SLAM) by enabling robots to build continuous, differentiable, and high-fidelity 3D maps from sensor data. However, as the scale and…

Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…

Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties…

The growing density of satellites in low-Earth orbit (LEO) presents serious challenges to space sustainability, primarily due to the increased risk of in-orbit collisions. Traditional ground-based tracking systems are constrained by latency…

Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations. Existing SOP methods typically aggregate contextual features to assist the occupancy representation…

In the past years modern mathematical methods for image analysis have led to a revolution in many fields, from computer vision to scientific imaging. However, some recently developed image processing techniques successfully exploited by…

As the popularity of on-orbit operations grows, so does the need for precise navigation around unknown resident space objects (RSOs) such as other spacecraft, orbital debris, and asteroids. The use of Simultaneous Localization and Mapping…

In this work, we explore the use of objects in Simultaneous Localization and Mapping in unseen worlds and propose an object-aided system (OA-SLAM). More precisely, we show that, compared to low-level points, the major benefit of objects…

Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…

Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal…

Although recently several foundation models for satellite remote sensing imagery have been proposed, they fail to address major challenges of real/operational applications. Indeed, embeddings that don't take into account the spectral,…

The goal of perception for autonomous vehicles is to extract semantic representations from multiple sensors and fuse these representations into a single "bird's-eye-view" coordinate frame for consumption by motion planning. We propose a new…