point cloud
PulseAugur coverage of point cloud — every cluster mentioning point cloud across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New method infers hidden skeletal landmarks from external soft-tissue geometry
Researchers have developed a novel method for inferring hidden skeletal landmarks from external soft-tissue geometry using computed tomography (CT) scans. This "Surface-to-Skeleton 3D Cephalometry" approach aims to esti…
-
New mathematical distances for partial optimal transport unveiled
Researchers have introduced new mathematical tools, entropic partial optimal transport and a partial mixture Gromov--Wasserstein distance, designed to compare probability measures and metric measure spaces. These method…
-
New framework generates 3D print G-code directly from point clouds
Researchers have developed a new framework called PrintAnything that generates 3D printing G-code directly from 3D point clouds, bypassing the need for mesh reconstruction. This method addresses issues with mesh artifac…
-
New method approximates diffusion processes on differential forms
Researchers have developed a novel data-driven method to approximate the projected ambient connection Laplacian, which operates on differential forms over Riemannian manifolds sampled by point clouds. This approach exte…
-
Trans-Unet enhances 3D point-cloud learning for brain folding prediction
Researchers have developed Trans-Unet, a novel framework designed to improve the accuracy and efficiency of 3D point-cloud learning for predicting brain folding patterns. This approach transforms 3D point-cloud data int…
-
New research details 3D point cloud attribute compression via deep unrolling
A new research paper on arXiv introduces a method for compressing attributes of 3D point clouds. The approach utilizes a multi-resolution B-spline framework and a feed-forward network derived from rate-distortion optimi…
-
New sampling method enables machine learning on variable-sized inputs
Researchers have introduced a novel framework for machine learning models that can handle inputs of varying sizes, such as point clouds, sequences, and graphs. This approach utilizes random sampling maps to compare and …
-
New NumGrad-Pull Method Enhances 3D Surface Reconstruction
Researchers have developed a new method called NumGrad-Pull for reconstructing continuous surfaces from unoriented and unordered 3D point clouds. This approach utilizes a tri-plane representation to accelerate the learn…
-
Poisoning attacks evade data augmentation in 3D point cloud datasets for AVs
A new research paper investigates the impact of poisoning attacks on augmented 3D point cloud datasets, particularly for connected and autonomous vehicles. The study finds that data augmentation techniques, such as Gene…
-
New multimodal LLM enhances understanding of indoor building components
Researchers have developed Building-MLLM, a novel multimodal large language model designed for understanding indoor building components from point cloud data. This model integrates point clouds with natural language ins…
-
DriveWeaver enhances autonomous driving simulations with point-conditioned video inpainting
Researchers have developed DriveWeaver, a new framework designed to improve autonomous driving simulations by inserting vehicles with specific trajectories into existing scenes. This method uses video inpainting conditi…
-
New EPMF method improves 3D semantic segmentation with multi-sensor fusion
Researchers have developed EPMF, an efficient method for multi-sensor fusion in 3D semantic segmentation. This technique enhances scene understanding for applications like autonomous driving by effectively combining vis…
-
TriMM model integrates multi-modal data for enhanced 3D generation
Researchers have introduced TriMM, a novel feed-forward generative model designed for high-quality 3D asset creation. TriMM uniquely integrates features from multiple modalities, such as RGB images, RGBD data, and point…
-
SpatialSV framework enhances MLLMs' 3D spatial awareness with interpretable visual supervision
Researchers have introduced SpatialSV, a novel framework aimed at enhancing the 3D spatial awareness of multimodal large language models (MLLMs). Unlike existing methods that rely on external tools or opaque feature dis…
-
New method estimates object pose without 3D models using rotational symmetry
Researchers have developed a novel method for object pose estimation from point clouds that does not require known 3D models. This approach leverages the rotational symmetry inherent in many industrial objects to overco…
-
New methods tackle 3D geometry reconstruction for deformable and multi-object scenes
Two new research papers introduce novel methods for reconstructing 3D geometry from point-cloud data. ParCo-SDF focuses on deformable objects, enabling prior-free reconstruction by encoding temporal geometry similaritie…
-
New Metric--Phase Fields improve 3D reconstruction of thin structures
Researchers have developed a new method called Metric--Phase Fields (MPFs) to improve the reconstruction of thin structures from unoriented point clouds. Unlike existing methods that struggle with thin or open geometrie…
-
New t-FCW graph representation enhances point cloud analysis
Researchers have developed an enhanced transposed Fully Connected Weighted (t-FCW) graph representation to embed point clouds into a metric space. This new method analyzes the properties that make t-FCW effective, leadi…