Related papers: C-Drag: Chain-of-Thought Driven Motion Controller …
Shot transitions play a pivotal role in multi-shot video generation, as they determine the overall narrative expression and the directorial design of visual storytelling. However, recent progress has primarily focused on low-level visual…
In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera…
Emotional talking-head generation has emerged as a pivotal research area at the intersection of computer vision and multimodal artificial intelligence, with its core value lying in enhancing human-computer interaction through immersive and…
The narrative quality of a video fundamentally determines its perceptual value. Although existing video generation methods can produce visually appealing content, they predominantly rely on sparse conditioning signals such as text prompts…
We propose a novel framework, On-Demand MOtion Generation (ODMO), for generating realistic and diverse long-term 3D human motion sequences conditioned only on action types with an additional capability of customization. ODMO shows…
While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this…
Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process. To address these issues, we propose a unified framework capable of generating…
Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects. Open-Vocabulary Multi-Object Tracking (OVMOT) addresses this by enabling…
Real-time in-between motion generation is universally required in games and highly desirable in existing animation pipelines. Its core challenge lies in the need to satisfy three critical conditions simultaneously: quality, controllability…
Multi-contact motion is important for humanoid robots to work in various environments. We propose a centroidal online trajectory generation and stabilization control for humanoid dynamic multi-contact motion. The proposed method features…
Many Vision-Language-Action (VLA) models are built upon an internal world model trained via next-frame prediction ``$v_t \rightarrow v_{t+1}$''. However, this paradigm attempts to predict the future frame's appearance directly, without…
Animating images with interactive motion control has garnered popularity for image-to-video (I2V) generation. Modern approaches typically rely on large Gaussian kernels to extend motion trajectories as condition without explicitly defining…
Recent advancements in diffusion models have greatly improved the quality and diversity of synthesized content. To harness the expressive power of diffusion models, researchers have explored various controllable mechanisms that allow users…
This paper presents DriVerse, a generative model for simulating navigation-driven driving scenes from a single image and a future trajectory. Previous autonomous driving world models either directly feed the trajectory or discrete control…
When humans grasp an object, they naturally form trajectories in their minds to manipulate it for specific tasks. Modeling hand-object interaction priors holds significant potential to advance robotic and embodied AI systems in learning to…
We present a novel approach for hand-object action recognition that leverages 2D point tracks as an additional motion cue. While most existing methods rely on RGB appearance, human pose estimation, or their combination, our work…
Generating realistic animated videos from static images is an important area of research in computer vision. Methods based on physical simulation and motion prediction have achieved notable advances, but they are often limited to specific…
Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive…
In this paper, we aim to model 3D scene geometry, appearance, and physical information just from dynamic multi-view videos in the absence of any human labels. By leveraging physics-informed losses as soft constraints or integrating simple…
Video composition is the core task of video editing. Although image composition based on diffusion models has been highly successful, it is not straightforward to extend the achievement to video object composition tasks, which not only…