Related papers: A Heteroscedastic Likelihood Model for Two-frame O…

Most mobile robots follow a modular sense-planact system architecture that can lead to poor performance or even catastrophic failure for visual inertial navigation systems due to trajectories devoid of feature matches. Planning in belief…

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…

This paper presents an applied analysis of local and global methods, with a focus on the Horn-Schunck algorithm for optical flow computation. We explore the theoretical and practical aspects of local approaches, such as the Lucas-Kanade…

Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level, assuming objects are rigid bodies. However, these instance-level methods are…

Convolutional neural networks have shown to achieve superior performance on image segmentation tasks. However, convolutional neural networks, operating as black-box systems, generally do not provide a reliable measure about the confidence…

Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able to provide explanations for past events and rigorous…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Localization is an essential technique in mobile robotics. In a complex environment, it is necessary to fuse different localization modules to obtain more robust results, in which the error model plays a paramount role. However,…

The performance of flow matching and diffusion models can be greatly improved at inference time using reward alignment algorithms, yet efficiency remains a major limitation. While several algorithms were proposed, we demonstrate that a…

According to recent studies, commonly used computer vision datasets contain about 4% of label errors. For example, the COCO dataset is known for its high level of noise in data labels, which limits its use for training robust neural deep…

High-precision micromanipulation techniques, including optical tweezers and hydrodynamic trapping, have garnered wide-spread interest. Recent advances in optofluidic multiplexed assembly and microrobotics demonstrate significant progress,…

We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of…

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning systems, particularly in safety-critical applications. Likelihood-based deep generative models have historically faced criticism for their…

Forecasting motion and spatial positions of objects is of fundamental importance, especially in safety-critical settings such as autonomous driving. In this work, we address the issue by forecasting two different modalities that carry…

Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy are broken. To address this problem, we present an…

We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small displacement and constant…

Uncertainty plays a key role in future prediction. The future is uncertain. That means there might be many possible futures. A future prediction method should cover the whole possibilities to be robust. In autonomous driving, covering…

Autonomous robotics is critically affected by the robustness of its scene understanding algorithms. We propose a two-axis pipeline based on polarization indices to analyze dynamic urban scenes. As robots evolve in unknown environments, they…

In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of…

A machine learning method to predict steady external fluid flows using elliptic input features is introduced. Using data from as few as one high-fidelity simulation, the proposed method produces models generalizable under changes to…