Related papers: UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous…

The ability to detect and segment moving objects in a scene is essential for building consistent maps, making future state predictions, avoiding collisions, and planning. In this paper, we address the problem of moving object segmentation…

We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow…

We present ReFlow, a unified framework for monocular dynamic scene reconstruction that learns 3D motion in a novel self-correction manner from raw video. Existing methods often suffer from incomplete scene initialization for dynamic…

We reframe scene flow as the task of estimating a continuous space-time ODE that describes motion for an entire observation sequence, represented with a neural prior. Our method, EulerFlow, optimizes this neural prior estimate against…

Roadway free-flow speed captures the typical vehicle speed in low traffic conditions. Modeling free-flow speed is an important problem in transportation engineering with applications to a variety of design, operation, planning, and policy…

Robust and accurate perception of humans in their 3D scene context is essential for integrating robots into everyday environments. Existing approaches, however, often fail to predict plausible and accurate human motion estimates that are…

Estimation of unsteady flow fields around flight vehicles may improve flow interactions and lead to enhanced vehicle performance. Although flow-field representations can be very high-dimensional, their dynamics can have low-order…

State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation.…

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…

Large models have shown generalization across datasets for many low-level vision tasks, like depth estimation, but no such general models exist for scene flow. Even though scene flow has wide potential use, it is not used in practice…

The ability of predicting the future is important for intelligent systems, e.g. autonomous vehicles and robots to plan early and make decisions accordingly. Future scene parsing and optical flow estimation are two key tasks that help agents…

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D…

Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on…

3D Multi-Object Tracking (MOT) is an important part of the unmanned vehicle perception module. Most methods optimize object detection and data association independently. These methods make the network structure complicated and limit the…

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…

Camera-only 3D object detection is critical for autonomous driving, offering a cost-effective alternative to LiDAR based methods. In particular, multi-view 3D object detection has emerged as a promising direction due to its balanced…

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 present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher network, and uses these predictions as annotations to guide a student network…

LiDAR point clouds have become the most common data source in autonomous driving. However, due to the sparsity of point clouds, accurate and reliable detection cannot be achieved in specific scenarios. Because of their complementarity with…

Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion…