Related papers: VoteFlow: Enforcing Local Rigidity in Self-Supervi…

Recent semi-dense image matching methods have achieved remarkable success, but two long-standing issues still impair their performance. At the coarse stage, the over-exclusion issue of their mutual nearest neighbor (MNN) matching layer…

Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance…

Autonomous vehicle navigation is a key challenge in artificial intelligence, requiring robust and accurate decision-making processes. This research introduces a new end-to-end method that exploits multimodal information from a single…

In the paper, we propose a robust real-time visual odometry in dynamic environments via rigid-motion model updated by scene flow. The proposed algorithm consists of spatial motion segmentation and temporal motion tracking. The spatial…

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our approach is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such redundancy implicitly provides various…

Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion naturalness. Building on…

Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exclusions or semantic segmentations, which suffer from low…

Accurate and fast localization is vital for safe autonomous navigation in GPS-denied areas. Fine-Grained Cross-View Geolocalization (FG-CVG) aims to estimate the precise 2-Degree-of-Freedom (2-DoF) location of a ground image relative to a…

Likelihood-based deep generative models have been widely investigated for Image Anomaly Detection (IAD), particularly Normalizing Flows, yet their strict architectural invertibility needs often constrain scalability, particularly in…

Autonomous driving requires reasoning about interactions with surrounding traffic. A prevailing approach is large-scale imitation learning on expert driving datasets, aimed at generalizing across diverse real-world scenarios. For online…

3D single object tracking (SOT) is a crucial task in fields of mobile robotics and autonomous driving. Traditional motion-based approaches achieve target tracking by estimating the relative movement of target between two consecutive frames.…

This paper presents a novel architecture for simultaneous estimation of highly accurate optical flows and rigid scene transformations for difficult scenarios where the brightness assumption is violated by strong shading changes. In the case…

Many model-based Visual Odometry (VO) algorithms have been proposed in the past decade, often restricted to the type of camera optics, or the underlying motion manifold observed. We envision robots to be able to learn and perform these…

Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D…

Predicting the future occupancy states of the surrounding environment is a vital task for autonomous driving. However, current best-performing single-modality methods or multi-modality fusion perception methods are only able to predict…

Hydrodynamics simulations are powerful tools for studying fluid behavior under physical forces, enabling extraction of features that reveal key flow characteristics. Traditional post-analysis methods offer high accuracy but incur…

Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement…

Understanding 3D scenes is a critical prerequisite for autonomous agents. Recently, LiDAR and other sensors have made large amounts of data available in the form of temporal sequences of point cloud frames. In this work, we propose a novel…

Weakly supervised object detection (WSOD), which is an effective way to train an object detection model using only image-level annotations, has attracted considerable attention from researchers. However, most of the existing methods, which…

Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-based policies. However,…