Zhenbo Song
9 papers · 2020–2025 · 7 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 ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Computer Vision
(6)
Artificial Intelligence
(4)
Analysis
(4)
Core AI
(4)
Machine Learning
(3)
Processing
(3)
Deep Learning
(2)
Architectures
(1)
Core Methods
(1)
Domain-Specific
(1)
Generation
(1)
Learning Types
(1)
Models
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
point cloud
(2)
image generation
(1)
motion forecasting
(1)
pose estimation
(1)
emotion recognition
(1)
dense correspondence
(1)
image restoration
(1)
video restoration
(1)
3d scene understanding
(1)
camera localization
(1)
feature disentanglement
(1)
efficient computing
(1)
adversarial robustness
(1)
optical flow
(1)
motion generation
(1)
adversarial attack
(1)
diffusion model
(1)
disentangled representation
(1)
vision-language model
(1)
model compression
(1)
Papers
Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
ICLR 2025
Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction
NeurIPS 2024
Universal Video Face Restoration Method Based on Vision-Language Model
ACML 2024
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
ICCV 2023
Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization
NeurIPS 2023
Robust Single Image Reflection Removal Against Adversarial Attacks
CVPR 2023
Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation from Monocular RGB Image
ECCV 2022
SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
AAAI 2022
Deep Novel View Synthesis from Colored 3D Point Clouds
ECCV 2020