lidar
PulseAugur coverage of lidar — every cluster mentioning lidar across labs, papers, and developer communities, ranked by signal.
- used by Autonomous Vehicles 90%
- uses Camera 90%
- used by Carla 80%
- instance of Nuscenes 70%
- used by Nuscenes 70%
- used by SemanticKITTI 70%
- used by Camera 70%
- instance of SemanticKITTI 70%
- used by RGB color model 70%
- used by inertial navigation system 70%
- instance of Carla 70%
- affiliated with 4D radar 70%
- 2026-05-18 research_milestone A new method for imaging hidden objects using consumer LiDAR was published. source
22 day(s) with sentiment data
-
HiPFuse framework enhances real-time LiDAR semantic segmentation for edge devices
Researchers have developed HiPFuse, a novel framework for real-time LiDAR semantic segmentation designed for edge devices. This system effectively fuses point and Bird's-Eye-View (BEV) features, enhancing accuracy by co…
-
New LiDAR simulation framework URL-Sim enhances autonomous driving scene reconstruction
Researchers have developed URL-Sim, a novel framework for creating high-fidelity LiDAR simulations of dynamic driving scenes. This system addresses the slow rendering speeds of previous Neural Radiance Fields (NeRF) bas…
-
New method reconstructs power lines from incomplete LiDAR data
Researchers have developed a novel method for reconstructing power lines from incomplete LiDAR data, addressing challenges posed by vegetation occlusion and varying data modalities. The technique combines density-based …
-
Laser scanning accuracy for tree diameter estimation improved by new bias compensation method
A new study published on arXiv investigates the impact of laser beam width and measurement noise on the accuracy of tree diameter estimation using laser scanning. Researchers found that the heteroscedasticity of measure…
-
AI agents discover unmapped Maya site using NASA data
An individual utilized AI agents to analyze NASA LiDAR data, leading to the discovery of an unmapped Maya archaeological site in Mexico. The process, from initial idea to confirmation by Mexico's national archaeology in…
-
New FIND framework enhances LiDAR 3D detection by disentangling frequency domains
Researchers have introduced FIND (Frequency Invariance Disentanglement), a new framework designed to improve LiDAR-based 3D Object Detection (L3OD) performance by addressing domain shifts. FIND operates in the frequency…
-
New depth completion method extrapolates beyond LiDAR coverage
Researchers have developed a new method for depth completion that focuses on areas beyond direct LiDAR coverage, utilizing a frozen monocular depth foundation model. This approach integrates sparse LiDAR data with the m…
-
Diffusion models enhance event-camera depth estimation with eSharp
Researchers have developed eSharp, a new framework for monocular depth estimation that utilizes event cameras to overcome limitations in fast-motion and high-dynamic-range scenes. By repurposing diffusion models, eSharp…
-
GEDI mission data geolocation improved using super-resolved terrain models
Researchers have developed a method to improve the geolocation accuracy of data from the Global Ecosystem Dynamics Investigation (GEDI) mission, which uses a LiDAR instrument on the International Space Station. By super…
-
New HFX3D dataset advances urban facade understanding with functional LiDAR data
Researchers have introduced HFX3D, a new large-scale benchmark dataset for understanding urban building facades using LiDAR data. This dataset, comprising approximately 492 million LiDAR points from 26 buildings in Hali…
-
TrackCue framework enhances LiDAR scene flow estimation using image tracking
Researchers have developed TrackCue, a novel framework designed to improve LiDAR scene flow estimation by leveraging image-based point tracking. This method addresses limitations in existing approaches that rely solely …
-
FREE-LIVO method decouples LiDAR-camera sensors for robust odometry
Researchers have developed FREE-LIVO, a novel LiDAR-Inertial-Visual Odometry method that decouples the rigid mounting and precise time synchronization typically required between LiDAR and camera sensors. This approach u…
-
New LiDAR Transformer achieves real-time speed and higher accuracy
Researchers have developed a new Transformer-based approach for processing full-waveform LiDAR data, aiming to improve real-time performance and accuracy. The method, called FWL-ToPM, uses intensity-guided token reducti…
-
Marine vehicle navigation safety enhanced by vision-sensor fusion
This paper reviews advancements in navigational safety for marine surface vehicles, focusing on how intelligent vision and multi-sensor fusion techniques enhance situational awareness in restricted visibility. It covers…
-
New WayPOP benchmark tests autonomous vehicle perception on unknown objects
Researchers have introduced WayPOP, a new benchmark designed to evaluate the perception systems of autonomous vehicles. This benchmark focuses on open-set panoptic tracking, meaning it can identify and track objects tha…
-
New WV-GS framework synthesizes wide views from multiple cameras for autonomous driving
Researchers have developed Wide-View Gaussian Splatting (WV-GS), a novel framework for synthesizing a unified wide view from multiple overlapping perspective cameras, a crucial capability for autonomous driving systems.…
-
Epistemic uncertainty boosts 3D LiDAR point cloud segmentation accuracy
Researchers have explored the effectiveness of epistemic uncertainty estimates in training models for 3D LiDAR point cloud segmentation. The study investigated using uncertainty as an input feature and as a confidence w…
-
New WorkIng Dataset Enhances AV Navigation in Highway Work Zones
Researchers have introduced WorkIng, a new benchmark dataset designed to improve autonomous vehicle navigation in highway work zones. This dataset includes both real-world and synthetic data, addressing the limitations …
-
LiDAR-based token selection slashes compute for autonomous driving models
Researchers have developed a novel method called Geometry-Aware Token Selection (GATS) for autonomous driving models that significantly reduces computational load by selectively processing image tokens. By utilizing LiD…
-
New framework assesses adversarial robustness of LiDAR 3D perception models
Researchers have developed LiDAR-SHIELD, a comprehensive and Dockerized framework designed to assess the adversarial robustness of LiDAR-based 3D perception models. This framework simplifies the process by allowing any …