Yuan Liu

36

Papers

349

Total Citations

Papers (36)

GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors

Epona: Autoregressive Diffusion World Model for Autonomous Driving

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

CADDreamer: CAD Object Generation from Single-view Images

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

GAS: Generative Activation-Aided Asynchronous Split Federated Learning

OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization

Neural Rays for Occlusion-Aware Image-Based Rendering

F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories

NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies

Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting

Contrast and Order Representations for Video Self-Supervised Learning

Improving 3D Object Detection With Channel-Wise Transformer

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

Improving Pixel-based MIM by Reducing Wasted Modeling Capability

Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground

Object Tracking using Spatio-Temporal Networks for Future Prediction Location

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

GauUpdate: New Object Insertion in 3D Gaussian Fields with Consistent Global Illumination

OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning

M²N: A Progressive Macro-to-Micro 3D Modeling Scheme for Unveiling Drug-Target Affinity

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Multi-Granularity Generator for Temporal Action Proposal

PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation

Learnable Motion Coherence for Correspondence Pruning

Point2Skeleton: Learning Skeletal Representations from Point Clouds

The Blessings of Unlabeled Background in Untrimmed Videos

GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

Diagnosing failures of fairness transfer across distribution shift in real-world medical settings