Hao Zhao

34

Papers

119

Total Citations

Papers (34)

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

PhysGen3D: Crafting a Miniature Interactive World from a Single Image

Reversible Decoupling Network for Single Image Reflection Removal

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

Detect Anything 3D in the Wild

Training-Free Model Merging for Multi-target Domain Adaptation

GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis

Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

Analytical Lyapunov Function Discovery: An RL-based Generative Approach

Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation

Network Sketching: Exploiting Binary Structure in Deep CNNs

Deeply-Supervised Knowledge Synergy

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

High-Fidelity Human Avatars From a Single RGB Camera

Delving Into Shape-Aware Zero-Shot Semantic Segmentation

DPF: Learning Dense Prediction Fields With Weak Supervision

Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer

A Closed-Form Solution to Universal Style Transfer

3D Implicit Transporter for Temporally Consistent Keypoint Discovery

INT2: Interactive Trajectory Prediction at Intersections

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

SC-wLS: Towards Interpretable Feed-Forward Camera Re-localization

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning

PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model

UniScene: Unified Occupancy-centric Driving Scene Generation

InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data

SNAKE: Shape-aware Neural 3D Keypoint Field

TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation

PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection