Related papers: TopoMaskV2: Enhanced Instance-Mask-Based Formulati…
Sliding-window object detectors that generate bounding-box object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first…
Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they…
The representative instance segmentation methods mostly segment different object instances with a mask of the fixed resolution, e.g., 28*28 grid. However, a low-resolution mask loses rich details, while a high-resolution mask incurs…
2D top-down maps are commonly used for the navigation and exploration of mobile robots through unknown areas. Typically, the robot builds the navigation maps incrementally from local observations using onboard sensors. Recent works have…
Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their…
Instance segmentation is an important problem in computer vision, with applications in autonomous driving, drone navigation and robotic manipulation. However, most existing methods are not real-time, complicating their deployment in…
We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training…
Understanding lane toplogy relationships accurately is critical for safe autonomous driving. However, existing two-stage methods suffer from inefficiencies due to error propagations and increased computational overheads. To address these…
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…
Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated…
Uplink pre-compensation in ground-to-satellite optical links remains a problem, with an appropriate measurement of the wavefront error in the uplink path often not being available. We present a method that uses successive measurements of…
Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. However, due to their weak supervision nature, the MIL methods were susceptible…
Mathematically representing the shape of an object is a key ingredient for solving inverse rendering problems. Explicit representations like meshes are efficient to render in a differentiable fashion but have difficulties handling topology…
We introduce a novel framework for multiway point cloud mosaicking (named Wednesday), designed to co-align sets of partially overlapping point clouds -- typically obtained from 3D scanners or moving RGB-D cameras -- into a unified…
The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding…
In topology optimization of compliant mechanisms, the specific placement of boundary conditions strongly affects the resulting material distribution and performance of the design. At the same time, the most effective locations of the loads…
Making top-down human pose estimation method present both good performance and high efficiency is appealing. Mask RCNN can largely improve the efficiency by conducting person detection and pose estimation in a single framework, as the…
We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the…
Predicting a binary mask for an object is more accurate but also more computationally expensive than a bounding box. Polygonal masks as developed in CenterPoly can be a good compromise. In this paper, we improve over CenterPoly by enhancing…
We present TOPGN, a novel method for real-time transparent obstacle detection for robot navigation in unknown environments. We use a multi-layer 2D grid map representation obtained by summing the intensities of lidar point clouds that lie…