MapAnything
PulseAugur coverage of MapAnything — every cluster mentioning MapAnything across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New PrePARE method slashes memory use in multi-view geometry transformers
Researchers have developed PrePARE, a novel method for optimizing multi-view geometry transformers by pruning patch tokens before they enter the alternating-attention (AA) stack. This approach significantly reduces memo…
-
New G-ray encoding improves multi-view vision transformers under camera heterogeneity
Researchers have developed G-ray, a novel ray-level relative geometric position encoding designed for multi-view vision transformers. This method addresses challenges posed by camera heterogeneity, such as varying field…
-
New UAV3DCrop benchmark evaluates 3D crop reconstruction methods
A new benchmark dataset called UAV3DCrop has been introduced for evaluating 3D reconstruction methods in agricultural settings using unmanned aerial vehicles. The dataset comprises 88,830 images from 91 scenes across va…
-
MapAnything system automates urban asset mapping from single images
A new research paper introduces MapAnything, a system designed to automate the spatial mapping of urban objects and incidents using monocular depth estimation models. This framework converts 2D image data into 3D spatia…
-
New framework adapts 3D reconstruction models for fisheye lenses
Researchers have developed Fisheye3R, a new framework designed to adapt existing 3D reconstruction foundation models to effectively process images from fisheye lenses. These models, typically trained on standard perspec…
-
New FlexDepth models offer robust, real-time driving depth estimation · 4 sources tracked
Researchers have developed FlexDepth, a novel family of self-supervised monocular depth estimation models designed for complex driving environments. This approach addresses limitations of existing models, which struggle…