Free Information Center
HumanNeRF refers to a class of neural radiance field techniques specialized for free-viewpoint rendering of human subjects. It enables photorealistic 3D reconstruction and novel viewpoint synthesis of dynamic humans from multi-view images or video sequences.
Instant neural graphics primitive (Instant NGP) is a machine learning framework designed for efficient and rapid neural representation of 3D scenes. It utilizes a multi-resolution hash encoding to accelerate training and rendering of neural graphics primitives, enabling real-time applications in graphics and vision.
MixNeRF is a computational approach that integrates neural radiance fields with mixed reality applications to enable realistic rendering and interaction of 3D scenes. It leverages neural networks to model complex light transport and scene geometry, facilitating immersive augmented and virtual reality experiences.
DreamFusion is a text-to-3D synthesis method that generates three-dimensional models from textual descriptions using neural rendering and diffusion models. It enables the creation of 3D objects without requiring explicit 3D data inputs.
Animatable NeRF is an extension of Neural Radiance Fields (NeRF) technology that enables the representation and rendering of dynamic, deformable 3D scenes. It allows for the animation of objects or scenes by modeling changes in shape or pose over time.