Skip to search formSkip to main contentSkip to account menu

SketchiMo

SketchiMo solves for the motion given a set of projective constraints that relate the sketch inputs to the unknown 3D poses, and introduces the concept of sketch space, a contextual geometric representation of sketch targets that enhances, right on the viewport, different aspects of the motion.
ACM (opens in a new tab)

Facial retargeting with automatic range of motion alignment

This work forms the problem of transferring the blendshapes of a facial rig to an actor as a special case of manifold alignment, by exploring the similarities of the motion spaces defined by the blend shapes and by an expressive training sequence of the actor.
ACM (opens in a new tab)

SIGGRAPH: G: Interactive Rigging

A semi-automatic rigging editing framework is proposed which eases the need for manual intervention while maintaining an important degree of control over the final rig.

Sparse Rig Parameter Optimization for Character Animation

A novel motion retargeting method that efficiently estimates artist‐friendly rig space parameters while balancing the considerations of fidelity to the source motion and the ease of subsequent editing, and its effectiveness in simplifying any necessary manual editing within the production pipeline.
Wiley (opens in a new tab)

Virtual face sculpting

This paper introduces the new concept of virtual face sculpting, where the goal is to sculpt a virtual statue as if the human face was sculpted on the statue.
ACM (opens in a new tab)

Depth and texture imaging using time-varying color structured lights

The experimental results show that the proposed method for depth and texture imaging using time-varying color structured lights is suitable for static and slow moving objects.
IEEE (opens in a new tab)

SOMA: Unifying Parametric Human Body Models

SOMA is a unified body layer that bridges heterogeneous representations through three abstraction layers, letting practitioners freely mix identity sources and pose data at inference time, and is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp.
arXiv (opens in a new tab)

Stereoscopic image generation of background terrain scenes

This work presents a novel mesh refinement algorithm for the creation of stereoscopic images of terrain scenes that evaluates mesh errors utilising a texture projection onto the geometry and refines the mesh using Laplacian‐based editing.
Wiley (opens in a new tab)

Interactive rigging

Commercial applications such as Maya or 3DS Max provide many tool that support this process, including the 'joint tool' and the 'paint skin weights tool', but most of these tools are difficult to use for novice users.
ACM (opens in a new tab)

Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars

The technical aspects of NVIDIA Audio2Face-3D, including data acquisition, network architecture, retargeting methodology, evaluation metrics, and use cases are detailed, to assist digital avatar creators and game developers in generating realistic facial animations.
arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)