UniScene: Unified Occupancy-centric Driving Scene Generation

• URL: http://arxiv.org/abs/2412.05435v1
• Date: Fri, 06 Dec 2024 21:41:52 GMT
• Title: UniScene: Unified Occupancy-centric Driving Scene Generation
• Authors: Bohan Li, Jiazhe Guo, Hongsi Liu, Yingshuang Zou, Yikang Ding, Xiwu Chen, Hu Zhu, Feiyang Tan, Chi Zhang, Tiancai Wang, Shuchang Zhou, Li Zhang, Xiaojuan Qi, Hao Zhao, Mu Yang, Wenjun Zeng, Xin Jin,
• Abstract summary: We introduce UniScene, the first unified framework for generating three key data forms - semantic occupancy, video, and LiDAR.<n>UniScene employs a progressive generation process that decomposes the complex task of scene generation into two hierarchical steps.<n>Extensive experiments demonstrate that UniScene outperforms previous SOTAs in the occupancy, video, and LiDAR generation.
• Score: 73.22859345600192
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating high-fidelity, controllable, and annotated training data is critical for autonomous driving. Existing methods typically generate a single data form directly from a coarse scene layout, which not only fails to output rich data forms required for diverse downstream tasks but also struggles to model the direct layout-to-data distribution. In this paper, we introduce UniScene, the first unified framework for generating three key data forms - semantic occupancy, video, and LiDAR - in driving scenes. UniScene employs a progressive generation process that decomposes the complex task of scene generation into two hierarchical steps: (a) first generating semantic occupancy from a customized scene layout as a meta scene representation rich in both semantic and geometric information, and then (b) conditioned on occupancy, generating video and LiDAR data, respectively, with two novel transfer strategies of Gaussian-based Joint Rendering and Prior-guided Sparse Modeling. This occupancy-centric approach reduces the generation burden, especially for intricate scenes, while providing detailed intermediate representations for the subsequent generation stages. Extensive experiments demonstrate that UniScene outperforms previous SOTAs in the occupancy, video, and LiDAR generation, which also indeed benefits downstream driving tasks.

Related papers

• Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors [52.63385546943866]
  We present a text-to-scene generation method (namely, Layout2Scene) using additional semantic layout as the prompt to inject precise control of 3D object positions. To fully leverage 2D diffusion priors in geometry and appearance generation, we introduce a semantic-guided geometry diffusion model and a semantic-geometry guided diffusion model. Our method can generate more plausible and realistic scenes as compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-05T12:20:13Z)
• LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene Reconstruction [6.428928591765432]
  Gaussian Splatting (GS) facilitates real-time, rendering with an explicit 3D Gaussian representation of the scene. GS provides faster processing and more intuitive scene editing than the implicit Neural Radiance Fields (NeRFs) We propose a novel GS method for dynamic scene synthesis and editing with improved scene reconstruction through LiDAR supervision and support for LiDAR rendering.
  arXiv  Detail & Related papers  (2024-12-19T22:59:55Z)
• SSEditor: Controllable Mask-to-Scene Generation with Diffusion Model [8.664947484778486]
  SSEditor is a controllable Semantic Scene Editor that can generate specified target categories without multiple-step resampling. In the second stage, we introduce a geometric-semantic fusion module that enhance the model's ability to learn geometric and semantic information. experiments on the unseen Occ-3D dataset show that SSEditor is capable of generating novel urban scenes.
  arXiv  Detail & Related papers  (2024-11-19T07:19:05Z)
• MegaScenes: Scene-Level View Synthesis at Scale [69.21293001231993]
  Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. We create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. We analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency.
  arXiv  Detail & Related papers  (2024-06-17T17:55:55Z)
• SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior [53.52396082006044]
  Current methods struggle to maintain rendering quality at the viewpoint that deviates significantly from the training viewpoints. This issue stems from the sparse training views captured by a fixed camera on a moving vehicle. We propose a novel approach that enhances the capacity of 3DGS by leveraging prior from a Diffusion Model.
  arXiv  Detail & Related papers  (2024-03-29T09:20:29Z)
• InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior [27.773451301040424]
  InstructScene is a novel generative framework that integrates a semantic graph prior and a layout decoder. We show that the proposed method surpasses existing state-of-the-art approaches by a large margin.
  arXiv  Detail & Related papers  (2024-02-07T10:09:00Z)
• Joint Generative Modeling of Scene Graphs and Images via Diffusion Models [37.788957749123725]
  We present a novel generative task: joint scene graph - image generation. We introduce a novel diffusion model, DiffuseSG, that jointly models the adjacency matrix along with heterogeneous node and edge attributes. With a graph transformer being the denoiser, DiffuseSG successively denoises the scene graph representation in a continuous space and discretizes the final representation to generate the clean scene graph.
  arXiv  Detail & Related papers  (2024-01-02T10:10:29Z)
• CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion [83.30168660888913]
  We present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model.
  arXiv  Detail & Related papers  (2023-05-25T17:39:13Z)
• Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs [85.54212143154986]
  Controllable scene synthesis consists of generating 3D information that satisfy underlying specifications. Scene graphs are representations of a scene composed of objects (nodes) and inter-object relationships (edges) We propose the first work that directly generates shapes from a scene graph in an end-to-end manner.
  arXiv  Detail & Related papers  (2021-08-19T17:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.