Related papers: InteractPro: A Unified Framework for Motion-Aware …
Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often…
Image composition targets at synthesizing a realistic composite image from a pair of foreground and background images. Recently, generative composition methods are built on large pretrained diffusion models to generate composite images,…
We present ActionPlan, a unified motion diffusion framework that bridges real-time streaming with high-quality offline generation within a single model. The core idea is to introduce a per-frame action plan: the model predicts frame-level…
Motion planning is a crucial component of autonomous robot driving. While various trajectory datasets exist, effectively utilizing them for a target domain remains challenging due to differences in agent interactions and environmental…
We study the problem of generating intermediate images from image pairs with large motion while maintaining semantic consistency. Due to the large motion, the intermediate semantic information may be absent in input images. Existing methods…
This paper proposes an interaction and safety-aware motion-planning method for an autonomous vehicle in uncertain multi-vehicle traffic environments. The method integrates the ability of the interaction-aware interacting multiple model…
Human-robot collaborative applications require scene representations that are kept up-to-date and facilitate safe motions in dynamic scenes. In this letter, we present an interactive distance field mapping and planning (IDMP) framework that…
Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video…
Motion simulation, prediction and planning are foundational tasks in autonomous driving, each essential for modeling and reasoning about dynamic traffic scenarios. While often addressed in isolation due to their differing objectives, such…
Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with image regions-while their generative counterpart,…
Generating realistic human motions that naturally respond to both spoken language and physical objects is crucial for interactive digital experiences. Current methods, however, address speech-driven gestures or object interactions…
Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative,…
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…
Safely interacting with other traffic participants is one of the core requirements for autonomous driving, especially in intersections and occlusions. Most existing approaches are designed for particular scenarios and require significant…
While existing image-guided composition methods may help insert a foreground object onto a user-specified region of a background image, achieving natural blending inside the region with the rest of the image unchanged, we observe that these…
Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositional generation. In this paper, we propose RealCompo, a new…
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image…
Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during…
Many modern robotics applications require robots to function autonomously in dynamic environments including other decision making agents, such as people or other robots. This calls for fast and scalable interactive motion planning. This…
Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the…