Yinda Zhang

44

Papers

80

Total Citations

Papers (44)

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image

Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes

DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model

HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation

IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular VideosC

Neural Pose Transfer by Spatially Adaptive Instance Normalization

Holistic 3D Scene Understanding From a Single Image With Implicit Representation

Spatially-Varying Outdoor Lighting Estimation From Intrinsics

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences

Learning Compositional Representation for 4D Captures With Neural ODE

Density-Preserving Deep Point Cloud Compression

H4D: Human 4D Modeling by Learning Neural Compositional Representation

SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field

Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions

Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos

Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur

DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation

Multiresolution Deep Implicit Functions for 3D Shape Representation

Deep Hybrid Self-Prior for Full 3D Mesh Generation

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering

Interacting Two-Hand 3D Pose and Shape Reconstruction From Single Color Image

DeepPanoContext: Panoramic 3D Scene Understanding With Holistic Scene Context Graph and Relation-Based Optimization

Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor

Novel-View Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views

Learning Versatile 3D Shape Generation with Improved Auto-regressive Models

Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects

Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images

DeepSFM: Structure From Motion Via Deep Bundle Adjustment

Du²Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels

GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes

DELTAR: Depth Estimation from a Light-Weight ToF Sensor and RGB Image

PRIF: Primary Ray-Based Implicit Function

NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing

LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling

Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks

Deep Depth Completion of a Single RGB-D Image

DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image

Deep Implicit Volume Compression

DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing

Neural Point Cloud Rendering via Multi-Plane Projection