@DisneyResearchHub - 268 本の動画
チャンネル登録者数 13.1万人
Disney Research is a network of research labs that collaborate closely with academic institutions We're able to combine the best of academia and industry: we...
Neural Facial Deformation Transfer
Autonomous Human-Robot Interaction via Operator Imitation
CLIP-Fusion: A Spatio-Temporal Quality Metric for Frame Interpolation
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Factorized Motion Diffusion for Precise and Character Agnostic Motion Inbetweening video
Skel-inbetweening for Intuitive Neural Motion Authoring
RobotKeyframing: Learning Locomotion with High Level Objectives
Lossy Image Compression with Foundation Diffusion Models Video
Spline-based Transformers
Robot Motion Diffusion Model: Motion Generation for Robotic Characters
VMP: Versatile Motion Priors for Robustly Tracking Motion on Physical Characters
Learning a Generalized Physical Face Model From Data Video
Controllable Neural Style Transfer for Dynamic Meshes Video
Design and Control of a Bipedal Robotic Character
Infinite 3D Landmarks: Improving Continuous 2D FacialLandmark Detection
Stylize My Wrinkles: Bridging the Gap from Simulation to Reality
QUADify: Extracting Meshes with Pixel-level Details and Materials from Images
Artist-Friendly Relightable and Animatable Neural Heads
Anatomically Constrained Implicit Face Models
Soft Pneumatic Actuator Design using Differentiable Simulation
Interactive Design of Stylized Walking Gaits for Robotic Characters
The Impulse Particle-In-Cell Method
Fast Dynamic Facial Wrinkles
Name Pronunciation Extraction and Reuse in Human-Agent Conversation
Trajectory Augmentation for Robust Neural Locomotion Controllers
Optimal Design of Robotic Character Kinematics Video
Pose and Skeleton Aware Neural IK
An Implicit Physical Face Model Driven by Expression and Style
A Perceptual Shape Loss for Monocular 3D Face Reconstruction
Transformer-based Neural Augmentation of Robot Simulation Representations
ReNeRF:Relightable Neural Radiance Fields with Nearfield Lighting
Kernel-Based Frame Interpolation for Spatio-Temporally Adaptive Rendering
DOC: Differentiable Optimal Control for Retargeting Motions onto Legged Robots
GraphSimulationForSkinMicroWrinkles Video
Video Compression with Entropy-Constrained Neural Representations
Continuous Landmark Detection with 3D Queries
Kernel Aware Resampler
Frame Interpolation Transformer and Uncertainty Guidance
Physics-Informed Neural Corrector for Deformation-based Fluid
Self-Supervised Effective Resolution Estimation with Adversarial Augmentations
Efficient Neural Style Transfer For Volumetric Simulations
Production Ready Face Re Aging for Visual Effects
TempFormer: Temporally Consistent Transformer for Video Denoising
Learning Dynamic 3D Geometry and Texture for Video Face Swapping
Facial Animation with Disentangled Identity and Motion using Transformers
MoRF: Morphable Radiance Fields for Multiview Neural Head Modeling
Facial Hair Tracking for High Fidelity Performance Capture
Local Anatomically-Constrained Facial Performance Retargeting
Implicit Neural Representation for Physics-driven Actuated Soft Bodies
Shape Transformers: Topology-Independent 3D Shape Models Using Transformers
Improved Lighting Models for Facial Appearance Capture
Neural Frame Interpolation for Rendered Content
Rendering with Style Combining Traditional and Neural Approaches for High Quality Face Rendering
Adaptive Convolutions for Structure-Aware Style Transfer
A Versatile Inverse Kinematics Formulation for Retargeting Motions onto Robots with Kinematic Loops
FaceMagic: Real-time Facial Detail Effects on Mobile
ADD: Analytically Differentiable Dynamics for Multi -Body Systems with Frictional Contact
Automated Routing of Muscle Fibers for Soft Robots
RobotSculptor: Artist-Directed Robotic Sculpting of Clay
Designing Robotically-Constructed Metal Frame Structures
Semantic Deep Face Models
Realistic and Interactive Robot Gaze
Realistic and Interactive Robot Gaze
Data-driven Extraction and Composition of Secondary Dynamics in Facial Performance Capture
Single Shot High Quality Facial Geometry and Skin Appearance Capture
Rig space Neural Rendering
Interactive Sculpting of Digital Faces Using an Anatomical Modeling Paradigm
High Resolution Neural Face Swapping for Visual Effects
Attention Driven Cropping for Very High Resolution Facial Landmark Detection
Fast Nonlinear Least Squares Optimization of Large Scale Semi Sparse Problems
Facial Expression Synthesis using a Global-Local Multilinear Framework
PoseMMR: A Collaborative Mixed Reality Authoring Tool for Character Animation
MakeSense: Automated Sensor Design for Proprioceptive Soft Robots
X-CAD: Optimizing CAD Models with Extended Finite Elements
Recycling a Landmark Dataset for Real-time Face Tracking with Low Cost HMD Integrated Cameras
Fast Handovers with a Robot Character: Small Sensorimotor Delays Improve Perceived Qualities
Towards a Natural Motion Generator: a Pipeline to Control a Humanoid based on Motion Data
Parameterized Animated Activities
Vibration-Minimizing Motion Retargeting for Robotic Characters
Neural Importance Sampling
Accurate Markerless Jaw Tracking for Facial Performance Capture
Tangent Space Optimization of Controls for Character Animation
Practical Person Specific Eye Rigging
Trajectory-based Probabilistic Policy Gradient for Learning Locomotion Behaviors
Animating an Autonomous 3D Talking Avatar
Set-In-Stone: Worst-Case Optimization of Structures Weak in Tension
Bend-It: Design and Fabrication of Kinetic Wire Characters
Appearance Capture and Modeling of Human Teeth
Practical Dynamic Facial Appearance Modeling and Acquisition
PuppetPhone: Puppeteering Virtual Characters Using a Smartphone
AR Costumes: Automatically Augmenting Watertight Costumes from a single RGB Image
Designing Groundless Body Channel Communication Systems: Performance and Implications
PaintCopter: An Autonomous UAV for Spray Painting on 3D Surfaces
StreetMap - Mapping and Localization on Ground Planes using a Downward Facing Camera
Design and Fabrication of a Bipedal Robot using Serial-Parallel Hybrid Leg Mechanism
Keys-to-Sim: Transferring Hand-Crafted Key-framed Animations to Simulated Figures
Denoising Deep Monte Carlo Renderings
Deep Video Color Propagation
An Omnistereoscopic Video Pipeline for Capture and Display of Real-World VR
Denoising with Kernel Prediction and Asymmetric Loss Functions
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
2321 回視聴 - 5 か月前
Factorized Motion Diffusion for Precise and Character Agnostic Motion Inbetweening video
5800 回視聴 - 5 か月前
VMP: Versatile Motion Priors for Robustly Tracking Motion on Physical Characters
1.7万 回視聴 - 8 か月前