~ similar to 2610.26857· 20 results
VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…
Cheng-De Fan, Chun-Wei Tuan Mu, Chen-Wei Chang, Chin-Yang Lin +3 more
This paper proposes LongE2V, a method for high-quality video recovery from sparse event streams using pre-trained video diffusion priors.
Xinyin Ma, Julius Berner, Chao Liu, Arash Vahdat +2 more
This paper introduces Flex-Forcing, a framework for video generation that enables a model to operate under both bidirectional and autoregressive generation regimes, achieving better video quality and…
This paper introduces Video Diffusion Avatars, a method for creating photo-realistic, multi-view consistent avatars from a single image.
Woojung Han, Seil Kang, Youngjun Jun, Min-Hung Chen +2 more
The paper proposes PhaseLock, a training-free framework that preserves physical consistency in image-to-video diffusion models by extracting a motion prior from few-step inference.
This paper introduces ElasticTTT, a framework to preserve the generative prior in Test-Time Tuning (TTT) of pretrained diffusion models for video editing, preventing Prior Collapse.
VidPrism introduces a novel heterogeneous Mixture-of-Experts framework that specializes temporal processing by dividing labor among experts, achieving state-of-the-art performance in image-to-video tr…
This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.
Haoxuan Wu, Lai Man Po, Mengyang Liu, Kun Li +2 more
The paper introduces PRISM, a method for decoding preference signals from noisy latents using a lightweight Query-based Aggregation head and a frozen video diffusion backbone, achieving state-of-the-a…
Jiayi Wu, Haoming Cai, Cornelia Fermuller, Christopher Metzler +1 more
Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…
This paper introduces MFlow, an adaptive parameterization for pixel-space diffusion models that learns to interpolate between two prediction methods, and ConvRefiner, a lightweight module to improve h…
Yuheng Chen, Teng Hu, Yuji Wang, Qingdong He +2 more
The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generat…
Jingyun Liang, Min Wei, Shikai Li, Yizeng Han +4 more
The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on re…
Jiahao He, Yihua Shao, Zhengkai Zhao, Pan Gao +5 more
The paper presents GrainGS, a dynamic Gaussian framework for scene reconstruction that balances fine-grained motion modeling, structural stability, and compact representation.
Shuaiwei Wang, Shi Li, Jieting Xu, Yuchi Huo +3 more
The paper introduces Texture++, a framework for enhancing low-resolution textures in 3D assets using a diffusion-based super-resolution model and adaptive view selection strategy.
The paper introduces LongVQUBench, a comprehensive benchmark for long-term video quality understanding with 1200 diverse videos and 1500 questions.
Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu +3 more
The paper introduces vid2vid-long, a correspondence-based approach to improve long-range temporal consistency in video-to-video translation.