6 papers
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Qi Zhao, Qirui Li, Hanlin Tang +10
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from bloc…
Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
Qirui Li, Guangcong Zheng, Qi Zhao +4
The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current…
Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection
Yehao Lu, Minghe Weng, Zekang Xiao +5
The Mixture of Experts (MoE) architecture has excelled in Large Vision-Language Models (LVLMs), yet its potential in real-time open-vocabulary object detectors, which also leverage…
RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control
Teng Li, Guangcong Zheng, Rui Jiang +9
Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. Ho…
RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements
Guangcong Zheng, Teng Li, Xianpan Zhou +1
Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K…
CamI2V: Camera-Controlled Image-to-Video Diffusion Model
Guangcong Zheng, Teng Li, Rui Jiang +3
Recent advancements have integrated camera pose as a user-friendly and physics-informed condition in video diffusion models, enabling precise camera control. In this paper, we iden…