Related papers: Zero-shot High-fidelity and Pose-controllable Char…
Human animation aims to generate temporally coherent and visually consistent videos over long sequences, yet modeling long-range dependencies while preserving frame quality remains challenging. Inspired by the human ability to leverage past…
Image animation aims to bring static images to life according to driving videos and create engaging visual content that can be used for various purposes such as animation, entertainment, and education. Recent unsupervised methods utilize…
Recent advancements in text-to-image generation have enabled significant progress in zero-shot 3D shape generation. This is achieved by score distillation, a methodology that uses pre-trained text-to-image diffusion models to optimize the…
Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can…
Generating controllable videos conforming to user intentions is an appealing yet challenging topic in computer vision. To enable maneuverable control in line with user intentions, a novel video generation task, named Text-Image-to-Video…
Pose transfer of human videos aims to generate a high fidelity video of a target person imitating actions of a source person. A few studies have made great progress either through image translation with deep latent features or neural…
Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit…
Recent advancements have integrated camera pose as a user-friendly and physics-informed condition in video diffusion models, enabling precise camera control. In this paper, we identify one of the key challenges as effectively modeling noisy…
Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methods fail to produce accurate and natural motion sequences due to a lack of…
Modeling virtual agents with behavior style is one factor for personalizing human agent interaction. We propose an efficient yet effective machine learning approach to synthesize gestures driven by prosodic features and text in the style of…
Current diffusion models for human image animation struggle to ensure identity (ID) consistency. This paper presents StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without…
Over recent years, diffusion models have facilitated significant advancements in video generation. Yet, the creation of face-related videos still confronts issues such as low facial fidelity, lack of frame consistency, limited editability…
Animal Pose Estimation and Tracking (APT) is a critical task in detecting and monitoring the keypoints of animals across a series of video frames, which is essential for understanding animal behavior. Past works relating to animals have…
Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrative. However, existing multi-shot video generation (MSV) methods struggle to…
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection…
Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora, like HowTo100M, offer rich resources for model training, they present significant…
Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case…
Close-proximity human-human interactive poses convey rich contextual information about interaction dynamics. Given such poses, humans can intuitively infer the context and anticipate possible past and future dynamics, drawing on strong…
Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often…
Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical…