Zhenghao Zhang

Zhenghao Zhang, Junchao Liao, Menghao Li et al.

Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with controllable motion remains an area of limited exploration. This paper introduces Tora, the first trajectory-oriented DiT framework that concurrently integrates textual, visual, and trajectory conditions, thereby enabling scalable video generation with effective motion guidance. Specifically, Tora consists of a Trajectory Extractor (TE), a Spatial-Temporal DiT, and a Motion-guidance Fuser (MGF). The TE encodes arbitrary trajectories into hierarchical spacetime motion patches with a 3D motion compression network. The MGF integrates the motion patches into the DiT blocks to generate consistent videos that accurately follow designated trajectories. Our design aligns seamlessly with DiT's scalability, allowing precise control of video content's dynamics with diverse durations, aspect ratios, and resolutions. Extensive experiments demonstrate that Tora excels in achieving high motion fidelity compared to the foundational DiT model, while also accurately simulating the complex movements of the physical world. Code is made available at https://github.com/alibaba/Tora .

Zhenghao Zhang, Fangtao Shao, Zuozhuo Dai et al.

Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. In this paper, we observe the temporal information is important as well and we propose TAFormer to aggregate spatio-temporal features both in transformer encoder and decoder. Specifically, in transformer encoder, we propose a novel spatio-temporal joint multi-scale deformable attention module which dynamically integrates the spatial and temporal information to obtain enriched spatio-temporal features. In transformer decoder, we introduce a temporal self-attention module to enhance the frame level box queries with the temporal relation. Moreover, TAFormer adopts an instance level contrastive loss to increase the discriminability of instance query embeddings. Therefore the tracking error caused by visually similar instances can be decreased. Experimental results show that TAFormer effectively leverages the spatial and temporal information to obtain context-aware feature representation and outperforms state-of-the-art methods.

Zhenghao Zhang, Zuozhuo Dai, Long Qin et al.

Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video editing methods commonly require per-video fine-tuning of diffusion models or specific inversion optimization to ensure high-fidelity edits. In this paper, we introduce EffiVED, an efficient diffusion-based model that directly supports instruction-guided video editing. To achieve this, we present two efficient workflows to gather video editing pairs, utilizing augmentation and fundamental vision-language techniques. These workflows transform vast image editing datasets and open-world videos into a high-quality dataset for training EffiVED. Experimental results reveal that EffiVED not only generates high-quality editing videos but also executes rapidly. Finally, we demonstrate that our data collection method significantly improves editing performance and can potentially tackle the scarcity of video editing data. Code can be found at https://github.com/alibaba/EffiVED.