YuAn Liu
- Papers
- 32
Cite
Notes
Only stored in your browser.
Authored papers
32Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
arXiv 2026
UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
arXiv 2026
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
arXiv 2026
UniRecGen: Unifying Multi-View 3D Reconstruction and Generation
arXiv 2026
POINTS-GUI-G: GUI-Grounding Journey
arXiv 2026
AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing
arXiv 2026
HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images
arXiv 2026
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
arXiv 2025
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
arXiv 2025
Reconstructing 4D Spatial Intelligence: A Survey
arXiv 2025
MOSPA: Human Motion Generation Driven by Spatial Audio
arXiv 2025
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
arXiv 2025
TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
arXiv 2025
SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence
arXiv 2025
MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds
arXiv 2025
SPATIALGEN: Layout-guided 3D Indoor Scene Generation
arXiv 2025
Epona: Autoregressive Diffusion World Model for Autonomous Driving
ICCV 2025
GECO: Generative Image-to-3D within a SECOnd
arXiv 2024
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
arXiv 2024
Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
arXiv 2024
POINTS1.5: Building a Vision-Language Model towards Real World Applications
arXiv 2024
Improving Pixel-based MIM by Reducing Wasted Modeling Capability
ICCV 2023 1
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
arXiv 2023
F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
arXiv 2023
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
arXiv 2023
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
CVPR 2023 1
EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
arXiv 2023
Single-shot Quantum Signal Processing Interferometry
arXiv 2023
Bootstrap Embedding on a Quantum Computer
arXiv 2023
Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground
ICCV 2023 1
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
NeurIPS 2021 12
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
arXiv 2021
Affiliations
Frequent co-authors
10from 32 papers