Wenzhao Zheng

papers

1,352

total citations

papers (27)

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

CVPR 2023arXiv

441

citations

SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

ICCV 2023arXiv

331

citations

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

ICML 2025arXiv

214

citations

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

CVPR 2025arXiv

citations

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

CVPR 2025arXiv

citations

Attributable Visual Similarity Learning

CVPR 2022arXiv

citations

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

ICCV 2025arXiv

citations

Segment Any Motion in Videos

CVPR 2025arXiv

citations

SpectralAR: Spectral Autoregressive Visual Generation

ICCV 2025arXiv

citations

Token-Label Alignment for Vision Transformers

ICCV 2023arXiv

citations

OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions

ICCV 2023arXiv

citations

Path Choice Matters for Clear Attributions in Path Methods

ICLR 2024arXiv

citations

UniDrive: Towards Universal Driving Perception Across Camera Configurations

ICLR 2025arXiv

citations

D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection

ICCV 2025

citations

Deep Factorized Metric Learning

CVPR 2023

citations

Authentic 4D Driving Simulation with a Video Generation Model

ICCV 2025

citations

Structural Deep Metric Learning for Room Layout Estimation

ECCV 2020

citations

Dynamic Metric Learning with Cross-Level Concept Distillation

ECCV 2022

citations

Learning Counterfactually Decoupled Attention for Open-World Model Attribution

ICCV 2025arXiv

citations

PlaneRAS: Learning Planar Primitives for 3D Plane Recovery

ICCV 2025

citations

LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction

CVPR 2024

citations

Deep Metric Learning via Adaptive Learnable Assessment

CVPR 2020

citations

Deep Compositional Metric Learning

CVPR 2021

citations

Dimension Embeddings for Monocular 3D Object Detection

CVPR 2022

citations

Wenzhao Zheng

papers (27)

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

Deep Relational Metric Learning

GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

Attributable Visual Similarity Learning

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

Segment Any Motion in Videos

SpectralAR: Spectral Autoregressive Visual Generation

Token-Label Alignment for Vision Transformers

OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions

Path Choice Matters for Clear Attributions in Path Methods

UniDrive: Towards Universal Driving Perception Across Camera Configurations

D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection

Deep Factorized Metric Learning

Authentic 4D Driving Simulation with a Video Generation Model

Structural Deep Metric Learning for Room Layout Estimation

Dynamic Metric Learning with Cross-Level Concept Distillation

Learning Counterfactually Decoupled Attention for Open-World Model Attribution

PlaneRAS: Learning Planar Primitives for 3D Plane Recovery

LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction

Deep Metric Learning via Adaptive Learnable Assessment

Deep Compositional Metric Learning

Dimension Embeddings for Monocular 3D Object Detection

papers (27)

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

Deep Relational Metric Learning

GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

Attributable Visual Similarity Learning

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

Segment Any Motion in Videos

SpectralAR: Spectral Autoregressive Visual Generation

Token-Label Alignment for Vision Transformers

OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions

Path Choice Matters for Clear Attributions in Path Methods

UniDrive: Towards Universal Driving Perception Across Camera Configurations

D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection

Deep Factorized Metric Learning

Authentic 4D Driving Simulation with a Video Generation Model

Structural Deep Metric Learning for Room Layout Estimation

Dynamic Metric Learning with Cross-Level Concept Distillation

Learning Counterfactually Decoupled Attention for Open-World Model Attribution

PlaneRAS: Learning Planar Primitives for 3D Plane Recovery

LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction

Deep Metric Learning via Adaptive Learnable Assessment

Deep Compositional Metric Learning

Dimension Embeddings for Monocular 3D Object Detection