6 papers
Fast-SAM3D: 3Dfy Anything in Images but Faster
Weilun Feng, Mingqiang Wu, Zhiliang Chen +10
SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the \textbf{firs…
RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
Kaicheng Yang, Xun Zhang, Haotong Qin +4
Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance over U-Net architectures. Howeve…
QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
Weilun Feng, Chuanguang Yang, Haotong Qin +8
Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment. Model quantization and atte…
TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search
Kaicheng Yang, Kaisen Yang, Baiting Wu +5
Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance.…
QuantFace: Efficient Quantization for Face Restoration
Jiatong Li, Libo Zhu, Haotong Qin +5
Diffusion models have been achieving remarkable performance in face restoration. However, the heavy computations hamper the widespread adoption of these models. In this work, we pr…
BiDM: Pushing the Limit of Quantization for Diffusion Models
Xingyu Zheng, Xianglong Liu, Yichen Bian +5
Diffusion models (DMs) have been significantly developed and widely used in various applications due to their excellent generative qualities. However, the expensive computation and…