paper-with-me

Papers

Tora: Trajectory-oriented Diffusion Transformer for Video Generation

2024-07-31 · CVPR 2025 1 · Zhenghao Zhang, Junchao Liao, Menghao Li, Zuozhuo Dai, Bingxue Qiu, Siyu Zhu, Long Qin, Weizhi Wang

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 video 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 Tora's excellence in achieving high motion fidelity, while also meticulously simulating the intricate movement of the physical world. Code is available at: https://github.com/alibaba/Tora.

📄 PDF Abstract BibTeX arXiv:2407.21705

Code (1)

alibaba/Tora 공식 구현 pytorch

Tasks

Video CompressionVideo Generation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation

2025-07-08 · Zhenghao Zhang, Junchao Liao, Xiangyu Meng, Long Qin 외

Recent advances in diffusion transformer models for motion-guided video generation, such as Tora, have shown significant progress. In this paper, we present Tora2, an enhanced version of Tora, which introduces several de…

Video Generation

DiTVR: Zero-Shot Diffusion Transformer for Video Restoration

2025-08-11 · Sicheng Gao, Nancy Mehta, Zongwei Wu, Radu Timofte arxiv

Video restoration aims to reconstruct high quality video sequences from low quality inputs, addressing tasks such as super resolution, denoising, and deblurring. Traditional regression based methods often produce unreali…

Video Restoration

Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models

2026-04-13 · Jinhui Hou, Zhiyu Zhu, Junhui Hou arxiv

Diffusion bridge models have shown great promise in image restoration by explicitly connecting clean and degraded image distributions. However, they often rely on complex and high-cost trajectories, which limit both samp…

Image Restoration

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

2025-01-02 · CVPR 2025 1 · Jianyi Wang, Zhijie Lin, Meng Wei, Yang Zhao 외

Video restoration poses non-trivial challenges in maintaining fidelity while recovering temporally consistent details from unknown degradations in the wild. Despite recent advances in diffusion-based restoration, these m…

Video Restoration

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models

2025-08-22 · Huanpeng Chu, Wei Wu, Guanyu Fen, Yutao Zhang arxiv

Diffusion models have emerged as a powerful paradigm for generative tasks such as image synthesis and video generation, with Transformer architectures further enhancing performance. However, the high computational cost o…

Video Generation