#temporal consistency
9 resultsTemporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion
Henglin Liu, Fangyuan Kong, Jing Wang +7
The paper introduces concentrated Implicit Preference Optimization (cIPO), a post‑training method for text‑to‑video diffusion models that derives preference signals from reconstruc…
4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
Renlong Wu, Haoran Chen, Yuxiang Wei +3
The paper introduces 4DHumanDiff, a diffusion-based framework that directly generates 360-degree dynamic human models as 4D Gaussian Splatting representations from text prompts, el…
WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models
Jiamin Xu, Cong Wang, Zheng Dong +4
The paper introduces WildShadowRemover, a system that fine‑tunes a pretrained video diffusion model to remove shadows from real‑world videos while preserving fine details and tempo…
LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relighting
Zixin Guo, Yehonathan Litman, Yifeng He +3
LightCrafter introduces a hybrid method that first renders a video with physically‑based rendering under the target lighting and then refines it with a diffusion model, enabling co…
LVMark: Robust Watermark for Latent Video Diffusion Models
Youngdong Jang, MinHyuk Jang, JaeHyeok Lee +4
The paper presents LVMark, a method for embedding invisible, robust watermarks into videos generated by latent video diffusion models, using a temporally consistent decoder and imp…
ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning
Zhao Yang, Yinan Shi, Mingyuan Yao +3
ChunkFlow introduces a seam‑aware training and execution framework for chunked robot policies that reduces boundary jitter by using deterministic overlap blending and continuity lo…
Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
Yuxin Huang, Ziming Hong, Mingming Gong +3
The paper introduces Temporally Consistent Universal Adversarial Perturbations (TC-UAP) to protect videos from both image-to-video and fine‑tuning based personalization attacks, en…
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Zhenhua Wu, Yun Pang, Mingkun Chang +4
The paper introduces RealityBridge, a framework that improves edited 3D Gaussian Splatting driving videos by removing rendering artifacts, harmonizing illumination, and ensuring te…
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
Zihan Su, Teng Hu, Jiangning Zhang +4
The paper introduces Cycle-World, a framework that uses reverse‑prediction cycle consistency to reduce error accumulation in long‑horizon video generation, improving temporal consi…