Related papers: Coordinate-Based Dual-Constrained Autoregressive M…

Diffusion models have shown excellent performance in text-to-image generation. Nevertheless, existing methods often suffer from performance bottlenecks when handling complex prompts that involve multiple objects, characteristics, and…

Text-to-motion generation has advanced rapidly, yet two challenges persist. First, existing motion autoencoders compress each frame into a single monolithic latent vector, entangling trajectory and per-joint rotations in an unstructured…

Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle…

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation process is an important goal moving forward and recent…

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens. However,…

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation…

We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation without considering scenes due to the limited availability of…

Diffusion models have recently gained significant attention in robotics due to their ability to generate multi-modal distributions of system states and behaviors. However, a key challenge remains: ensuring precise control over the generated…

Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference…

Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on.…

Text-to-Motion (T2M) generation aims to synthesize realistic human motion sequences from natural language descriptions. While two-stage frameworks leveraging discrete motion representations have advanced T2M research, they often neglect…

Existing music-driven dance generation approaches have achieved strong realism and effective audio-motion alignment. However, they generally lack semantic controllability, making it difficult to guide specific movements through natural…

Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion…

Autoregressive and diffusion models represent two complementary generative paradigms. Autoregressive models excel at sequential planning and constraint composition, yet struggle with tasks that require explicit spatial or physical…

Diffusion models have emerged as a widely utilized and successful methodology in human motion synthesis. Task-oriented diffusion models have significantly advanced action-to-motion, text-to-motion, and audio-to-motion applications. In this…

3D human motion generation has seen substantial advancement in recent years. While state-of-the-art approaches have improved performance significantly, they still struggle with complex and detailed motions unseen in training data, largely…

Text-driven human motion generation, as one of the vital tasks in computer-aided content creation, has recently attracted increasing attention. While pioneering research has largely focused on improving numerical performance metrics on…

Controllable generation of 3D human motions becomes an important topic as the world embraces digital transformation. Existing works, though making promising progress with the advent of diffusion models, heavily rely on meticulously captured…

Co-speech gesture generation has significantly advanced human-computer interaction, yet speaker movements remain constrained due to the omission of text-driven non-spontaneous gestures (e.g., bowing while talking). Existing methods face two…