Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning

• URL: http://arxiv.org/abs/2410.24219v1
• Date: Thu, 31 Oct 2024 17:59:53 GMT
• Title: Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
• Authors: Penghui Ruan, Pichao Wang, Divya Saxena, Jiannong Cao, Yuhui Shi,
• Abstract summary: We propose a novel framework called DEcomposed MOtion (DEMO) to enhance motion synthesis in Text-to-Video (T2V) generation. Our method includes a content encoder for static elements and a motion encoder for temporal dynamics, alongside separate content and motion conditioning mechanisms. We demonstrate DEMO's superior ability to produce videos with enhanced motion dynamics while maintaining high visual quality.
• Score: 26.44634685830323
• License:
• Abstract: Despite advancements in Text-to-Video (T2V) generation, producing videos with realistic motion remains challenging. Current models often yield static or minimally dynamic outputs, failing to capture complex motions described by text. This issue stems from the internal biases in text encoding, which overlooks motions, and inadequate conditioning mechanisms in T2V generation models. To address this, we propose a novel framework called DEcomposed MOtion (DEMO), which enhances motion synthesis in T2V generation by decomposing both text encoding and conditioning into content and motion components. Our method includes a content encoder for static elements and a motion encoder for temporal dynamics, alongside separate content and motion conditioning mechanisms. Crucially, we introduce text-motion and video-motion supervision to improve the model's understanding and generation of motion. Evaluations on benchmarks such as MSR-VTT, UCF-101, WebVid-10M, EvalCrafter, and VBench demonstrate DEMO's superior ability to produce videos with enhanced motion dynamics while maintaining high visual quality. Our approach significantly advances T2V generation by integrating comprehensive motion understanding directly from textual descriptions. Project page: https://PR-Ryan.github.io/DEMO-project/

Related papers

• Text-Animator: Controllable Visual Text Video Generation [149.940821790235]
  We propose an innovative approach termed Text-Animator for visual text video generation. Text-Animator contains a text embedding injection module to precisely depict the structures of visual text in generated videos. We also develop a camera control module and a text refinement module to improve the stability of generated visual text.
  arXiv  Detail & Related papers  (2024-06-25T17:59:41Z)
• VideoTetris: Towards Compositional Text-to-Video Generation [45.395598467837374]
  VideoTetris is a framework that enables compositional T2V generation. We show that VideoTetris achieves impressive qualitative and quantitative results in T2V generation.
  arXiv  Detail & Related papers  (2024-06-06T17:25:33Z)
• LivePhoto: Real Image Animation with Text-guided Motion Control [51.31418077586208]
  This work presents a practical system, named LivePhoto, which allows users to animate an image of their interest with text descriptions. We first establish a strong baseline that helps a well-learned text-to-image generator (i.e., Stable Diffusion) take an image as a further input. We then equip the improved generator with a motion module for temporal modeling and propose a carefully designed training pipeline to better link texts and motions.
  arXiv  Detail & Related papers  (2023-12-05T17:59:52Z)
• ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation [33.37279673304]
  We introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text. ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method exhibits superior performance in terms of frame consistency, clip score, and conditional accuracy, outperforming other compared methods.
  arXiv  Detail & Related papers  (2023-10-11T17:46:28Z)
• Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning [16.094271750354835]
  Motion information is critical to a robust and generalized video representation. Recent works have adopted frame difference as the source of motion information in video contrastive learning. We present a framework capable of introducing well-aligned and significant motion information.
  arXiv  Detail & Related papers  (2023-09-01T07:03:27Z)
• Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs [112.39389727164594]
  Text-to-video (T2V) synthesis has gained increasing attention in the community, in which the recently emerged diffusion models (DMs) have promisingly shown stronger performance than the past approaches. While existing state-of-the-art DMs are competent to achieve high-resolution video generation, they may largely suffer from key limitations (e.g., action occurrence disorders, crude video motions) with respect to the temporal dynamics modeling, one of the crux of video synthesis. In this work, we investigate strengthening awareness of video dynamics for DMs, for high-quality T2V generation
  arXiv  Detail & Related papers  (2023-08-26T08:31:48Z)
• Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning [50.60891619269651]
  Control-A-Video is a controllable T2V diffusion model that can generate videos conditioned on text prompts and reference control maps like edge and depth maps. We propose novel strategies to incorporate content prior and motion prior into the diffusion-based generation process. Our framework generates higher-quality, more consistent videos compared to existing state-of-the-art methods in controllable text-to-video generation.
  arXiv  Detail & Related papers  (2023-05-23T09:03:19Z)
• LaMD: Latent Motion Diffusion for Video Generation [69.4111397077229]
  latent motion diffusion (LaMD) framework consists of a motion-decomposed video autoencoder and a diffusion-based motion generator. Results show that LaMD generates high-quality videos with a wide range of motions, from dynamics to highly controllable movements.
  arXiv  Detail & Related papers  (2023-04-23T10:32:32Z)
• Text-driven Video Prediction [83.04845684117835]
  We propose a new task called Text-driven Video Prediction (TVP) Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. To investigate the capability of text in causal inference for progressive motion information, our TVP framework contains a Text Inference Module (TIM)
  arXiv  Detail & Related papers  (2022-10-06T12:43:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.