Related papers: Terra: Explorable Native 3D World Model with Point…

Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting…

The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, existing approaches often suffer from a substantial visual and…

Single-image 3D generation has emerged as a prominent research topic, playing a vital role in virtual reality, 3D modeling, and digital content creation. However, existing methods face challenges such as a lack of multi-view geometric…

Despite the remarkable developments achieved by recent 3D generation works, scaling these methods to geographic extents, such as modeling thousands of square kilometers of Earth's surface, remains an open challenge. We address this through…

While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on…

End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we…

We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling, scaling to generation of entire room-scale scenes which can be…

We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing…

Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor…

Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians…

This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on variational autoencoders (VAEs) to generate discrete occupancy tokens, which inherently…

We present a novel deep generative model based on non i.i.d. variational autoencoders that captures global dependencies among observations in a fully unsupervised fashion. In contrast to the recent semi-supervised alternatives for global…

Point clouds are rich geometric data structures, where their three dimensional structure offers an excellent domain for understanding the representation learning and generative modeling in 3D space. In this work, we aim to improve the…

We propose ArtiLatent, a generative framework that synthesizes human-made 3D objects with fine-grained geometry, accurate articulation, and realistic appearance. Our approach jointly models part geometry and articulation dynamics by…

3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of…

Recent advances in video generation enable a new paradigm for 3D scene creation: generating camera-controlled videos that simulate scene walkthroughs, then lifting them to 3D via feed-forward reconstruction techniques. This generative…

Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of…

Generating high-fidelity, seamless textures directly on 3D surfaces, what we term 3D-native texturing, remains a fundamental open challenge, with the potential to overcome long-standing limitations of UV-based and multi-view projection…

Existing diffusion-based 3D scene generation methods primarily operate in 2D image/video latent spaces, which makes maintaining cross-view appearance and geometric consistency inherently challenging. To bridge this gap, we present OneWorld,…

World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially…