7 papers
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Baorui Ma, Jiahui Yang, Donglin Di +5
Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camer…
DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes
Qirui Hou, Wenzhang Sun, Chang Zeng +3
Real-time, high-fidelity reconstruction of dynamic driving scenes is challenged by complex dynamics and sparse views, with prior methods struggling to balance quality and efficienc…
PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes
Ying A, Wenzhang Sun, Chang Zeng +3
Reconstructing dynamic 3D urban scenes is crucial for autonomous driving, yet current methods face a stark trade-off between fidelity and computational cost. This inefficiency stem…
QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation
Jiahui Yang, Yongjia Ma, Donglin Di +6
Existing text-to-image models often rely on parameter fine-tuning techniques such as Low-Rank Adaptation (LoRA) to customize visual attributes. However, when combining multiple LoR…
UniCP: A Unified Caching and Pruning Framework for Efficient Video Generation
Wenzhang Sun, Qirui Hou, Donglin Di +3
Diffusion Transformers (DiT) excel in video generation but encounter significant computational challenges due to the quadratic complexity of attention. Notably, attention differenc…
UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control
Wenzhang Sun, Xiang Li, Donglin Di +5
Recently, animating portrait images using audio input is a popular task. Creating lifelike talking head videos requires flexible and natural movements, including facial and head dy…