Song-Hai Zhang
27 papers · 2019–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (38) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(13)
🤝
Dynamic Duo
(16)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(130)
Top co-authors
Research topics
Computer Vision
(24)
Deep Learning
(18)
Analysis
(17)
Generation
(17)
Models
(10)
Architectures
(7)
Artificial Intelligence
(6)
Computer Science
(6)
Machine Learning
(6)
Applications
(6)
Learning Types · Deep Learning
(6)
Core AI
(5)
Learning Types · Machine Learning
(5)
Processing
(3)
Core Methods
(2)
Keywords
diffusion model
(8)
novel view synthesis
(6)
3d reconstruction
(6)
depth estimation
(4)
3d gaussian splatting
(3)
variational autoencoder
(3)
3d vision
(2)
point cloud
(2)
score distillation sampling
(2)
autonomous driving
(2)
3d generation
(2)
neural radiance field
(2)
transformer architecture
(2)
mesh generation
(2)
gaussian splatting
(2)
3d shape generation
(2)
neural rendering
(2)
generative model
(2)
text-to-3d generation
(2)
multi-view consistency
(2)
Papers
Lafite: A Generative Latent Field for 3D Native Texturing
CVPR 2026
TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification
CVPR 2026
DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
ICCV 2025
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
ICCV 2025
MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing
CVPR 2025
NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation
ICCV 2025
Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images
CVPR 2025
SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing
ICCV 2025
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
NeurIPS 2024
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
CVPR 2024
PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion
CVPR 2024
PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation
AAAI 2024
Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views
AAAI 2024
Text-to-3D with Classifier Score Distillation
ICLR 2024
Texture-GS: Disentangle the Geometry and Texture for 3D Gaussian Splatting Editing
ECCV 2024
Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers
CVPR 2024
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
CVPR 2024
CXTrack: Improving 3D Point Cloud Tracking With Contextual Information
CVPR 2023
DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation
CVPR 2023
Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts
ICCV 2023
MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors
ICCV 2023
PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
NeurIPS 2023
Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment
ECCV 2022
NeRFReN: Neural Radiance Fields With Reflections
CVPR 2022
Sketch2Model: View-Aware 3D Modeling From Single Free-Hand Sketches
CVPR 2021
Example-Guided Style-Consistent Image Synthesis From Semantic Labeling
CVPR 2019
Pose2Seg: Detection Free Human Instance Segmentation
CVPR 2019