Related papers: WorldFlow3D: Flowing Through 3D Distributions for …

In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging. This field relies on accurate perception,…

Recent advances in imitation learning for 3D robotic manipulation have shown promising results with diffusion-based policies. However, achieving human-level dexterity requires seamless integration of geometric precision and semantic…

Scene flow estimation is the task of describing 3D motion between temporally successive observations. This thesis aims to build the foundation for building scene flow estimators with two important properties: they are scalable, i.e. they…

We introduce a latent 3D representation that models 3D surfaces as probability density functions in 3D, i.e., p(x,y,z), with flow-matching. Our representation is specifically designed for consumption by machine learning models, offering…

3D scene generation is a core technology for gaming, film/VFX, and VR/AR. Growing demand for rapid iteration, high-fidelity detail, and accessible content creation has further increased interest in this area. Existing methods broadly follow…

In this paper, we propose Extend3D, a training-free pipeline for 3D scene generation from a single image, built upon an object-centric 3D generative model. To overcome the limitations of fixed-size latent spaces in object-centric models for…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Molecular structure generation is a fundamental problem that involves determining the 3D positions of molecules' constituents. It has crucial biological applications, such as molecular docking, protein folding, and molecular design. Recent…

Diffusion models generate images with an unprecedented level of quality, but how can we freely rearrange image layouts? Recent works generate controllable scenes via learning spatially disentangled latent codes, but these methods do not…

Guided synthesis of high-quality 3D scenes is a challenging task. Diffusion models have shown promise in generating diverse data, including 3D scenes. However, current methods rely directly on text embeddings for controlling the generation,…

Flow-based generative models have demonstrated promising performance across a broad spectrum of data modalities (e.g., image and text). However, there are few works exploring their extension to unordered data (e.g., spatial point set),…

Automated 3D scene generation is pivotal for applications spanning virtual reality, digital content creation, and Embodied AI. While computer graphics prioritizes aesthetic layouts, vision and robotics demand scenes that mirror real-world…

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields,…

Reliable anticipation of traffic accidents is essential for advancing autonomous driving systems. However, this objective is limited by two fundamental challenges: the scarcity of diverse, high-quality training data and the frequent absence…

Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering their use in editing scenes and training embodied AI agents. We…

Flow-based generative models have recently shown impressive performance for conditional generation tasks, such as text-to-image generation. However, current methods transform a general unimodal noise distribution to a specific mode of the…

We present Seen2Scene, the first flow matching-based approach that trains directly on incomplete, real-world 3D scans for scene completion and generation. Unlike prior methods that rely on complete and hence synthetic 3D data, our approach…

World generation is a fundamental capability for applications like video games, simulation, and robotics. However, existing approaches face three main obstacles: controllability, scalability, and efficiency. End-to-end scene generation…

Recently, 3D reconstruction and generation have demonstrated impressive novel view synthesis results, achieving high fidelity and efficiency. However, a notable conditioning gap can be observed between these two fields, e.g., scalable 3D…

Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to…