相关论文: 3D-Aware Implicit Motion Control for View-Adaptive…

Human-centric video generation has advanced rapidly, yet existing methods struggle to produce controllable and physically consistent Human-Object Interaction (HOI) videos. Existing works rely on dense control signals, template videos, or…

We present InfiniCube, a scalable method for generating unbounded dynamic 3D driving scenes with high fidelity and controllability. Previous methods for scene generation either suffer from limited scales or lack geometric and appearance…

Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation. These methods enable the synthesis of detailed and…

Creating dynamic, view-consistent videos of customized subjects is highly sought after for a wide range of emerging applications, including immersive VR/AR, virtual production, and next-generation e-commerce. However, despite rapid progress…

We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and…

This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically restricted to hands, in…

Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two…

From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of…

Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). Current methods predominantly rely on verbal descriptive…

Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from perception to action,…

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…

Controllable video generation has attracted significant attention, largely due to advances in video diffusion models. In domains such as autonomous driving, it is essential to develop highly accurate predictions for object motions. This…

Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction models, are fast and capable of producing stable body…

Recent unified 3D generation models have made remarkable progress in producing high-quality 3D assets from a single image. Notably, layout-aware approaches such as SAM3D can reconstruct multiple objects while preserving their spatial…

Recent techniques on implicit geometry representation learning and neural rendering have shown promising results for 3D clothed human reconstruction from sparse video inputs. However, it is still challenging to reconstruct detailed surface…

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention -…

Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these…

Despite tremendous recent progress in human video generation, generative video diffusion models still struggle to capture the dynamics and physics of human motions faithfully. In this paper, we propose a new framework for human video…

Pedestrian motion, due to its causal nature, is strongly influenced by domain gaps arising from discrepancies between training and testing data distributions. Focusing on 3D human pose estimation, this work presents a controllable human…