← Search

Tianrui Zhu

2 accepted papers

2026

Post-Training Quantization for Video Matting

ICLR 2026poster

Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model compression and acceleration. As an efficient approach, Post-Traini…

Cited by 0SourceScholar
2025

KV-Edit: Training-Free Image Editing for Precise Background Preservation

ICCV 2025poster

Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free appr…