Projects in Awesome Lists tagged with bvh

https://github.com/gkjohnson/three-mesh-bvh

A BVH implementation to speed up raycasting and enable spatial queries against three.js meshes.

acceleration bounds bounds-hierarchy bvh distance geometry graphics intersection mesh pathtracing performance point-cloud pointcloud raycast raytracing three-js three-mesh-bvh threejs tree webvr

Last synced: 28 Sep 2024

https://github.com/knightcrawler25/glsl-pathtracer

A toy physically based GPU path tracer (C++/OpenGL/GLSL)

bsdf bvh disney glsl gpu linux opengl path path-tracer path-tracing pathtracer pathtracing ray ray-tracing raytracer tracer tracing windows

Last synced: 30 Sep 2024

https://github.com/gkjohnson/three-gpu-pathtracer

Path tracing renderer and utilities for three.js built on top of three-mesh-bvh.

bvh geometry graphics mesh path path-tracer path-tracing performance raytracing renderer rendering rtx three-gpu-pathtracer three-js three-mesh-bvh threejs tracer webgl

Last synced: 28 Sep 2024

https://github.com/lighttransport/nanort

NanoRT, single header only modern ray tracing kernel.

bdpt bvh pathtracing ray raytracing

Last synced: 30 Sep 2024

https://github.com/madmann91/bvh

A modern C++ BVH construction and traversal library

bvh construction-algorithms cpp20 header-only raytracing traversal-algorithms

Last synced: 28 Sep 2024

https://github.com/FORTH-ModelBasedTracker/MocapNET

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

2d-to-3d 3d-animation 3d-pose-estimation bvh bvh-format computer-vision demo ensemble gesture-recognition mocap neural-network pose-estimation real-time rgb-images tensorflow webcam