LatentMove: Towards Complex Human Movement Video Generation

TL;DR

LatentMove is a novel DiT-based framework for generating realistic, complex human movement videos from a single image, addressing challenges in handling rapid and intricate motions with improved consistency and detail.

Contribution

We introduce LatentMove, a new framework with control mechanisms and tokens for better complex human motion video generation, along with a challenging dataset and evaluation metrics.

Findings

Significantly improves the quality of human motion videos.

Handles rapid and complex movements more effectively.

Provides new benchmarks and metrics for I2V generation.

Abstract

Image-to-video (I2V) generation seeks to produce realistic motion sequences from a single reference image. Although recent methods exhibit strong temporal consistency, they often struggle when dealing with complex, non-repetitive human movements, leading to unnatural deformations. To tackle this issue, we present LatentMove, a DiT-based framework specifically tailored for highly dynamic human animation. Our architecture incorporates a conditional control branch and learnable face/body tokens to preserve consistency as well as fine-grained details across frames. We introduce Complex-Human-Videos (CHV), a dataset featuring diverse, challenging human motions designed to benchmark the robustness of I2V systems. We also introduce two metrics to assess the flow and silhouette consistency of generated videos with their ground truth. Experimental results indicate that LatentMove substantially improves human animation quality--particularly when handling rapid, intricate movements--thereby pushing the boundaries of I2V generation. The code, the CHV dataset, and the evaluation metrics will be available at https://github.com/ --.