Lu Qi
- Papers
- 25
Cite
Notes
Only stored in your browser.
Authored papers
25SAMTok: Representing Any Mask with Two Words
arXiv 2026
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
arXiv 2025
BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
arXiv 2025
Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation
arXiv 2025
CyberV: Cybernetics for Test-time Scaling in Video Understanding
arXiv 2025
DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
arXiv 2025
AirSim360: A Panoramic Simulation Platform within Drone View
arXiv 2025
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
arXiv 2025
Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
ICCV 2025
Controllable 3D Outdoor Scene Generation via Scene Graphs
ICCV 2025
Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
ICCV 2025
An Empirical Study of GPT-4o Image Generation Capabilities
arXiv 2025
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
arXiv 2025
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
arXiv 2025
Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model
arXiv 2024
RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
arXiv 2024
Point Cloud Mamba: Point Cloud Learning via State Space Model
arXiv 2024
Video Prediction Transformers without Recurrence or Convolution
arXiv 2024
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
arXiv 2024
RelationBooth: Towards Relation-Aware Customized Object Generation
arXiv 2024
Pyramid Diffusion for Fine 3D Large Scene Generation
arXiv 2023
Dual Associated Encoder for Face Restoration
arXiv 2023
High-Quality Entity Segmentation
arXiv 2022
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
CVPR 2022 1
Path Aggregation Network for Instance Segmentation
path-aggregation-network-for-instance-1
Affiliations
Frequent co-authors
10from 25 papers