12 papers
FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion
Yuang Meng, Chenyang Wu, Xianshun Liu +7
Existing optical flow methods broadly follow two paradigms: iterative optimization and diffusion-based estimation. Iterative methods, exemplified by RAFT, achieve high accuracy thr…
Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset
Junyu Lou, Kai Chen, Weiyi You +3
Modern smartphones capture Live Photos, short video bursts surrounding a still image, offering a dynamic and engaging photographic experience. However, the cover photo and video co…
ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion
Yao Liu, Lishen Qu, Shihao Zhou +6
Multi-Exposure Fusion (MEF) effectively extends dynamic range, but practical deployment is hindered by motion-induced ghosting and the scarcity of high-quality dynamic benchmarks.…
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
Yuhao Wang, Mu Qiao, Haiwen Diao +5
Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution.…
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
Ruibin Li, Tao Yang, Fangzhou Ai +4
Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA i…
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
Yanjun Guo, Zhengqiang Zhang, Pengfei Wang +3
Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory m…