Search Results for "objects detection"

...Built on top of Detectron2 and PyTorch3D, Mesh R-CNN enables end-to-end 3D mesh prediction directly from single RGB images. The model learns to detect, segment, and reconstruct detailed 3D mesh representations of objects in natural images, bridging the gap between 2D perception and 3D understanding. Unlike voxel-based or point-based approaches, Mesh R-CNN uses a differentiable mesh representation, allowing it to efficiently refine surface geometry while maintaining high spatial detail. The system combines 2D detection from Mask R-CNN with 3D reasoning modules that output full mesh reconstructions aligned with the input image. ...

Sombrero is a fast wavelet image processing and object detection C library for astronomical images. Sombrero is named after the "Mexican Hat" shape of the wavelet masks used in image convolution and is released under the GNU LGPL library.

GLOBE_3D: GL Object Based Engine for 3D. GLOBE_3D is a free, open-source, real-time 3D Engine written in Ada, based on OpenGL. Up-to-date GL bindings - portal rendering - binary space partition - object I/O - tools for importing - and more... More information on... http://globe3d.sf.net Alire crate: https://alire.ada.dev/crates/globe_3d Mirror: https://github.com/zertovitch/globe-3d/

...The dataset consists of 15K annotated video clips supplemented with over 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes. In addition, to ensure geo-diversity, our dataset is collected from 10 countries across five continents. Along with the dataset, we are also sharing a 3D object detection solution for four categories of objects — shoes, chairs, mugs, and cameras.

House3D is a large-scale virtual 3D simulation environment designed to support research in embodied AI, reinforcement learning, and vision-language navigation. It provides more than 45,000 richly annotated indoor scenes sourced from the SUNCG dataset, covering diverse architectural layouts such as studios, multi-floor homes, and spaces with detailed furnishings and room types. Each environment includes fully labeled 3D objects, allowing agents to perceive and interact with their surroundings...

FreeSOLID is a library for collision detection of three-dimensional objects undergoing rigid motion and deformation. FreeSOLID is designed to be used in interactive 3D graphics applications.

...Rendering and processing of game assets in glTF, X3D, VRML, Collada, Spine and other formats. Many graphic effects including shadows, shaders, mirrors, screen effects. Animation, collision detection, 3D sound. Extensible system of 3D objects, with out-of-the-box levels, items, intelligent creatures and more. Desktop, mobile, web plugin. Also home of view3dscene - our full-featured VRML/X3D browser. The "Kambi VRML game engine" is renamed to "Castle Game Engine" (short name castle-engine). For commits and all current information see castle-engine project.

Motiontrack is a motion detection backend which simply and effective compares 2 images and checks for any objects which have moved. Works even with low quality and high flicker / snowstorm images. Will someday be able to recognize objects.

3D Engine featuring : Particles systems, hierarchical animation, portal rendering, collision detection via BSPs, ISOSurfaces managing, NURBS, animated parametric surfaces, 3DSMAX plugin export for maps & objects, fast rendering via OpenGL

Solid is a library for collision detection of three-dimensional objects undergoing rigid motion and deformation. Solid is designed to be used in interactive 3D graphics applications using a VRML-like scene graph.