Occupancy grid and occupancy network methods for autonomous driving — volumetric 3D environment representation for obstacle avoidance and free-space estimation.
To overcome this, we introduce SimBEV2X, an advanced synthetic data generation tool built on the CARLA simulator.
Engineering 7.0 · Research 8.0 · Business 5.5
To address this, we introduce GaussianSeed, a progressive multi-scale Gaussian occupancy prediction framework that organizes primitives into a coarse-to-fine hierarchy.
Engineering 5.5 · Research 7.0 · Business 5.0
To overcome these limitations, we propose a monocular 3D structural mapping framework tailored for horticultural plants via semantic scene completion.
Engineering 5.5 · Research 7.0 · Business 6.5
To address this limitation, we introduce RayOcc, an occlusion-aware ray occupancy framework that reformulates ray modeling as multi-label existence prediction.
Engineering 5.5 · Research 8.0 · Business 5.0
In response, we propose a continuous measure based on the proportion of unused vehicle capacity.
Engineering 5.0 · Research 7.0 · Business 5.0
To address this gap and advance radar-based multi-task learning, we propose \method, a 4D radar-camera framework for 360$^\circ$ full-scene perception, which models semantic occupancy as a persistent scene state rather than a terminal output.
Engineering 5.0 · Research 7.0 · Business 5.0
In this work, we present a novel framework that enhances a quadruped robot equipped with a LiDAR sensor and an upward-facing fisheye camera for real-time dynamic object detection and tracking.
Engineering 5.5 · Research 8.0 · Business 6.5
We present SparseOcc++, a geometry-aware sparse framework that explicitly decouples scene completion from semantic segmentation.
Engineering 5.5 · Research 7.0 · Business 5.0
In this paper, we introduce Text-Guided Representation for Instance Prediction (TGRIP), a novel framework that bridges this gap by injecting rich semantic priors into the instance prediction loop.
Engineering 7.5 · Research 8.5 · Business 5.0
To address this, we introduce a Resolution-Context Decoupled Architecture.
Engineering 5.5 · Research 8.0 · Business 6.0
We propose \textit{COVScene}, a pose-free semantic Gaussian framework that couples renderable Gaussian primitives with a dense semantic occupancy field through differentiable volumetric lifting.
Engineering 5.0 · Research 8.0 · Business 5.0
To overcome these limitations, we propose a bandwidth-efficient collaborative Vector Quantization Semantic Occupancy Prediction (VQSOP) framework.
Engineering 5.5 · Research 8.0 · Business 6.5
To achieve this, we design a novel forward-projection-based multi-modal Gaussian initialization module and a shared cross-modal Gaussian encoder that iteratively updates Gaussian properties based on an attention mechanism.
Engineering 5.5 · Research 8.0 · Business 5.0
In this work, we propose a Dual Range-Voxel Representation (DRVR) that leverages the range-view context and voxel-view geometry of single-sweep point clouds for 3D semantic occupancy prediction, eliminating the concerns associated with the multi-sweeps.
Engineering 5.5 · Research 7.0 · Business 5.0
In this paper, we introduce InfiniVerse, a unified pipeline for long-range, 2D-3D-aligned, and controllable synthesis of dynamic urban scenes from a single frame.
Engineering 5.5 · Research 8.0 · Business 6.0
To overcome these challenges, we introduce OWMDrive, a generative end-to-end driving framework built upon an Occupancy World Model for multi-step 3D occupancy forecasting, which serves as a conditional prior to guide diffusion-based planning.
Engineering 5.5 · Research 7.0 · Business 5.0
This letter proposes CascadeOcc, a novel occupancy world model that prioritizes intrinsic structural hierarchy over extrinsic auxiliary modalities for autonomous driving.
Engineering 5.0 · Research 8.5 · Business 5.0
To address this issue, we propose G2DP (Grid-Guided Diffusion Planning), a diffusion-based planner that directly enforces dense environmental constraints through inference-time guidance.
Engineering 5.5 · Research 8.0 · Business 5.0
4D millimeter-wave radar, with its four-dimensional measurement capabilities encompassing range, azimuth, elevation, and Doppler velocity, has overcome the elevation perception limitations of traditional 3D millimeter-wave radar.
Engineering 5.0 · Research 7.0 · Business 5.0
Abstract Purpose Shared e‑scooters are increasingly integrated into urban transport systems, yet their environmental performance depends strongly on design, utilisation, and end‑of‑life management.
Engineering 5.0 · Research 7.0 · Business 5.0