Related papers: Efficient Animation of Sparse Voxel Octrees for Re…
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…
In this paper we present an extension of Direct Sparse Odometry (DSO) to a monocular visual SLAM system with loop closure detection and pose-graph optimization (LDSO). As a direct technique, DSO can utilize any image pixel with sufficient…
The monocular visual-inertial odometry (VIO) based on the direct method can leverage all available pixels in the image to simultaneously estimate the camera motion and reconstruct the denser map of the scene in real time. However, the…
Robust stereo visual-inertial odometry (VIO) remains challenging in low-texture scenes and under abrupt illumination changes, where point features become sparse and unstable, leading to ambiguous association and under-constrained…
Accurate single-object tracking and short-term motion forecasting remain challenging under occlusion, scale variation, and temporal drift, which disrupt the temporal coherence required for real-time perception. We introduce…
The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only…
Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR products consist only of a headset and controllers,…
Fast appearance variations and the distractions of similar objects are two of the most challenging problems in visual object tracking. Unlike many existing trackers that focus on modeling only the target, in this work, we consider the…
This paper presents a novel fast machine learning method that leverages two techniques: Vector Embedding on Orthonormal Basis (VEOB) and Spectral Transform (ST). The VEOB converts the original data encoding into a vector embedding with…
Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of reconstruction quality and real-time performance, mainly due…
We propose a compact and efficient tetrahedral mesh representation to improve the ray-tracing performance. We reorder tetrahedral mesh data using a space-filling curve to improve cache locality. Most importantly, we propose an efficient ray…
Obstacle detection and tracking represent a critical component in robot autonomous navigation. In this paper, we propose ODTFormer, a Transformer-based model to address both obstacle detection and tracking problems. For the detection task,…
Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either not accurate, time-consuming in training…
Visual Inertial Odometry (VIO) is the task of estimating the movement trajectory of an agent from an onboard camera stream fused with additional Inertial Measurement Unit (IMU) measurements. A crucial subtask within VIO is the tracking of…
We present a local 3D voxel mapping framework for off-road path planning and navigation. Our method provides both hard and soft positive obstacle detection, negative obstacle detection, slope estimation, and roughness estimation. By using a…
Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment…
Sample based ray marching is an effective method for direct volume rendering of unstructured meshes. However, sampling such meshes remains expensive, and strategies to reduce the number of samples taken have received relatively little…
Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has proven effective as a global representation of scenes. However,…
Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce Direct3D-S2, a scalable 3D generation framework based on…
Optical flow captures the motion of pixels in an image sequence over time, providing information about movement, depth, and environmental structure. Flying insects utilize this information to navigate and avoid obstacles, allowing them to…