6 papers
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
Kaiqi Liu, Yunyao Mao, Ziqi Cai +8
MAVIN is a framework for generating multi-shot audio‑visual content with fine‑grained narrative control, using boundary‑aware attention to align temporal segments and ID‑aware prop…
Video Generation Models Are Inherent Lighting Estimators
Ziqi Cai, Shuchen Weng, Kaiqi Liu +5
Recovering dynamic environment maps from a single in-the-wild video is crucial for photorealistic rendering, yet remains a challenge. Recent video generation models can produce pho…
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Jing Wang, Xiangxin Zhou, Jiajun Liang +5
Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation…
STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative
Peixuan Zhang, Zijian Jia, Kaiqi Liu +3
While recent advancements in generative models have achieved remarkable visual fidelity in video synthesis, creating coherent multi-shot narratives remains a significant challenge.…
Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining
Qi Fan, Kaiqi Liu, Nian Liu +4
Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes in new domains, which is often challenging due to the diverse characteristics of target domains…
MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing
Jinghan Yu, Junhao Xiao, Zhiyuan Ma +6
Recent years have witnessed the success of diffusion models in image customization tasks. However, existing mask-guided human erasing methods still struggle in complex scenarios su…