Animate-X: Universal Character Image Animation with Enhanced Motion Representation

TL;DR

This work tackles universal character image animation, extending beyond humans to anthropomorphic characters. It introduces Animate-X, a latent diffusion framework augmented with a Pose Indicator that combines implicit motion gist from CLIP features and explicit pose perturbations to improve generalization. The authors also propose A^2Bench, a benchmark for evaluating animation on anthropomorphic characters. Experiments show Animate-X achieves superior identity preservation and motion consistency across both human and anthropomorphic datasets, demonstrating broad applicability and robustness.

Abstract

Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existing methods only apply to human figures, which usually do not generalize well on anthropomorphic characters commonly used in industries like gaming and entertainment. Our in-depth analysis suggests to attribute this limitation to their insufficient modeling of motion, which is unable to comprehend the movement pattern of the driving video, thus imposing a pose sequence rigidly onto the target character. To this end, this paper proposes Animate-X, a universal animation framework based on LDM for various character types (collectively named X), including anthropomorphic characters. To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner. The former leverages CLIP visual features of a driving video to extract its gist of motion, like the overall movement pattern and temporal relations among motions, while the latter strengthens the generalization of LDM by simulating possible inputs in advance that may arise during inference. Moreover, we introduce a new Animated Anthropomorphic Benchmark (A^2Bench) to evaluate the performance of Animate-X on universal and widely applicable animation images. Extensive experiments demonstrate the superiority and effectiveness of Animate-X compared to state-of-the-art methods.

Figures (15)

• Figure 1: Animations produced by Animate-X which extends beyond human to anthropomorphic characters with various body structures, e.g., without limbs, from games, animations, and posters.
• Figure 2: (a) The overview of our Animate-X. Given a reference image $I^r$, we first extract CLIP image feature $f^r_{\varphi}$ and latent feature $f^r_{e}$ via CLIP image encoder $\Phi$ and VAE encoder $\mathcal{E}$. The proposed Implicit Pose Indicator (IPI) and Explicit Pose Indicator (EPI) produce motion feature $f_i$ and pose feature $f_e$, respectively. $f_e$ is concatenated with the noised input $\epsilon$ along the channel dimension, then further concatenated with $f^r_{e}$ along the temporal dimension. This serves as the input to the diffusion model $\epsilon_\theta$ for progressive denoising. During the denoising process, $f^r_{\varphi}$ and $f_i$ provide appearance condition from $I^r$ and motion condition from $I^d_{1:F}$. At last, a VAE decoder $\mathcal{D}$ is adopted to map the generated latent representation $z_0$ to the animation video. (b) The detailed structure of Implicit Pose Indicator. (c) The pipeline of pose transformation by Explicit Pose Indicator.
• Figure 3: Examples from our $A^2$Bench.
• Figure 4: The illustration of comparison settings.
• Figure 5: Qualitative comparisons with state-of-the-art methods.