Human Video Translation via Query Warping
- URL: http://arxiv.org/abs/2402.12099v2
- Date: Tue, 21 May 2024 04:04:01 GMT
- Title: Human Video Translation via Query Warping
- Authors: Haiming Zhu, Yangyang Xu, Shengfeng He,
- Abstract summary: We present QueryWarp, a novel framework for temporally coherent human motion video translation.
We use appearance flows to warp the previous frame's query token, aligning it with the current frame's query.
This query warping imposes explicit constraints on the outputs of self-attention layers, effectively guaranteeing temporally coherent translation.
- Score: 38.9185553719231
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: In this paper, we present QueryWarp, a novel framework for temporally coherent human motion video translation. Existing diffusion-based video editing approaches that rely solely on key and value tokens to ensure temporal consistency, which scarifies the preservation of local and structural regions. In contrast, we aim to consider complementary query priors by constructing the temporal correlations among query tokens from different frames. Initially, we extract appearance flows from source poses to capture continuous human foreground motion. Subsequently, during the denoising process of the diffusion model, we employ appearance flows to warp the previous frame's query token, aligning it with the current frame's query. This query warping imposes explicit constraints on the outputs of self-attention layers, effectively guaranteeing temporally coherent translation. We perform experiments on various human motion video translation tasks, and the results demonstrate that our QueryWarp framework surpasses state-of-the-art methods both qualitatively and quantitatively.
Related papers
- Disentangle and denoise: Tackling context misalignment for video moment retrieval [16.939535169282262]
Video Moment Retrieval aims to locate in-context video moments according to a natural language query.
This paper proposes a cross-modal Context Denoising Network (CDNet) for accurate moment retrieval.
arXiv Detail & Related papers (2024-08-14T15:00:27Z) - Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [64.2445487645478]
Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio.
We present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation.
arXiv Detail & Related papers (2024-07-11T17:34:51Z) - Contextualized Diffusion Models for Text-Guided Image and Video Generation [67.69171154637172]
Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing.
We propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample.
We generalize our model to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing.
arXiv Detail & Related papers (2024-02-26T15:01:16Z) - LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video
Translation [21.815083817914843]
We propose a new zero-shot video-to-video translation framework, named textitLatentWarp.
Our approach is simple: to constrain the query tokens to be temporally consistent, we further incorporate a warping operation in the latent space.
Experiment results demonstrate the superiority of textitLatentWarp in achieving video-to-video translation with temporal coherence.
arXiv Detail & Related papers (2023-11-01T08:02:57Z) - RIGID: Recurrent GAN Inversion and Editing of Real Face Videos [73.97520691413006]
GAN inversion is indispensable for applying the powerful editability of GAN to real images.
Existing methods invert video frames individually often leading to undesired inconsistent results over time.
We propose a unified recurrent framework, named textbfRecurrent vtextbfIdeo textbfGAN textbfInversion and etextbfDiting (RIGID)
Our framework learns the inherent coherence between input frames in an end-to-end manner.
arXiv Detail & Related papers (2023-08-11T12:17:24Z) - Counterfactual Cross-modality Reasoning for Weakly Supervised Video
Moment Localization [67.88493779080882]
Video moment localization aims to retrieve the target segment of an untrimmed video according to the natural language query.
Recent works contrast the cross-modality similarities driven by reconstructing masked queries.
We propose a novel proposed counterfactual cross-modality reasoning method.
arXiv Detail & Related papers (2023-08-10T15:45:45Z) - Towards Tokenized Human Dynamics Representation [41.75534387530019]
We study how to segment and cluster videos into recurring temporal patterns in a self-supervised way.
We evaluate the frame-wise representation learning step by Kendall's Tau and the lexicon building step by normalized mutual information and language entropy.
On the AIST++ and PKU-MMD datasets, actons bring significant performance improvements compared to several baselines.
arXiv Detail & Related papers (2021-11-22T18:59:58Z) - Motion-blurred Video Interpolation and Extrapolation [72.3254384191509]
We present a novel framework for deblurring, interpolating and extrapolating sharp frames from a motion-blurred video in an end-to-end manner.
To ensure temporal coherence across predicted frames and address potential temporal ambiguity, we propose a simple, yet effective flow-based rule.
arXiv Detail & Related papers (2021-03-04T12:18:25Z)
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.