Chi Zhang

81

Papers

483

Total Citations

Papers (81)

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

MeshAnything V2: Artist-Created Mesh Generation with Adjacent Mesh Tokenization

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous Driving

Model-Free Offline Reinforcement Learning with Enhanced Robustness

BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models

InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild

Sim4Rec: Data-Free Model Extraction Attack on Sequential Recommendation

Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness

Joint Multiview Segmentation and Localization of RGB-D Images Using Depth-Induced Silhouette Consistency

DenseASPP for Semantic Segmentation in Street Scenes

Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification

Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering

CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning

RAVEN: A Dataset for Relational and Analogical Visual REasoNing

Re-Identification Supervised Texture Generation

CRNet: Cross-Reference Networks for Few-Shot Segmentation

Circle Loss: A Unified Perspective of Pair Similarity Optimization

DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers

Conditional Gaussian Distribution Learning for Open Set Recognition

ACRE: Abstract Causal REasoning Beyond Covariation

Few-Shot Incremental Learning With Continually Evolved Classifiers

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

End-to-End Human Object Interaction Detection With HOI Transformer

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior

End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve

Query Adaptive Similarity Measure for RGB-D Object Recognition

MeshStereo: A Global Stereo Model With Mesh Alignment Regularization for View Interpolation

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation

Re-ID Driven Localization Refinement for Person Search

Temporal Knowledge Consistency for Unsupervised Visual Representation Learning

DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection

Binocular Mutual Learning for Improving Few-Shot Classification

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

Meta Navigator: Search for a Good Adaptation Policy for Few-Shot Learning

Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction

Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds

Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification

ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution

DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration

Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives

KD-MVS: Knowledge Distillation Based Self-Supervised Learning for Multi-View Stereo

Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning

Adaptive Hardness Negative Sampling for Collaborative Filtering

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

Video-Bench: Human-Aligned Video Generation Benchmark

Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game

UniScene: Unified Occupancy-centric Driving Scene Generation

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control

Style Nursing with Spatial and Semantic Guidance for Zero-Shot Traffic Scene Style Transfer

DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman Problem

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning

Panacea: Panoramic and Controllable Video Generation for Autonomous Driving

Parameter-Efficient Fine-Tuning with Controls

Learning Perceptual Inference by Contrasting

Geometric All-way Boolean Tensor Decomposition

Learning Disentangled Representations of Videos with Missing Data

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

Causal Inference with Non-IID Data using Linear Graphical Models

Hierarchical Normalization for Robust Monocular Depth Estimation

On the Learning Mechanisms in Physical Reasoning

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

Evaluating and Inducing Personality in Pre-trained Language Models

Active Reasoning in an Open-World Environment

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

Interactive Visual Reasoning under Uncertainty

SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems