Related papers: LSD-3D: Large-Scale 3D Driving Scene Generation wi…
Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning. Although recent advances have shown promise in learning 3D models from 2D images, these methods…
Neural 3D scene reconstruction methods have achieved impressive performance when reconstructing complex geometry and low-textured regions in indoor scenes. However, these methods heavily rely on 3D data which is costly and time-consuming to…
Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving. Despite the efficacy of Neural Radiance Fields (NeRF) for driving scenes, 3D Gaussian Splatting (3DGS)…
Urban modeling is essential for city planning, scene synthesis, and gaming. Existing image-based methods generate diverse layouts but often lack geometric continuity and scalability, while graph-based methods capture structural relations…
Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes,…
Understanding 3D scenes in open-world settings poses fundamental challenges for vision and robotics, particularly due to the limitations of closed-vocabulary supervision and static annotations. To address this, we propose a unified…
3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…
Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement,…
Existing lane-level simulation road network generation is labor-intensive, resource-demanding, and costly due to the need for large-scale data collection and manual post-editing. To overcome these limitations, we propose automatically…
How can one efficiently generate high-quality, wide-scope 3D scenes from arbitrary single images? Existing methods suffer several drawbacks, such as requiring multi-view data, time-consuming per-scene optimization, distorted geometry in…
We present a method to map 2D image observations of a scene to a persistent 3D scene representation, enabling novel view synthesis and disentangled representation of the movable and immovable components of the scene. Motivated by the…
Directly generating scenes from satellite imagery offers exciting possibilities for integration into applications like games and map services. However, challenges arise from significant view changes and scene scale. Previous efforts mainly…
Three-dimensional scene generation is crucial in computer vision, with applications spanning autonomous driving, gaming and the metaverse. Current methods either lack user control or rely on imprecise, non-intuitive conditions. In this…
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…
Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generated multi-view images, leading to low-quality 3D generation…
The generation of 3D scenes from user-specified conditions offers a promising avenue for alleviating the production burden in 3D applications. Previous studies required significant effort to realize the desired scene, owing to limited…
This study aims to investigate the challenge of insufficient three-dimensional context in synthetic datasets for scene text rendering. Although recent advances in diffusion models and related techniques have improved certain aspects of…
Simultaneous reconstruction of geometry and reflectance properties in uncontrolled environments remains a challenging problem. In this paper, we propose an efficient method to reconstruct the scene's 3D geometry and reflectance from…
Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout…
3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…