Lune

AAAI2025Top-tier venue

ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images

Hongyuan Liu, Haochen Yu, Bochao Zou, Juntao Lyu, Qi Mei, Jiansheng Chen, Huimin Ma

Abstract

Reconstructing 3D models from sensor data is a valuable and promising direction for developing testing and validation environments in applications like autonomous driving. However, existing methods for 3D modeling often rely on extensive multi-view data or controlled conditions, making them difficult and expensive to scale. Furthermore, these methods, particularly those based on neural radiance fields, typically produce implicit models that can be challenging to manipulate and suffer from slow rendering speeds. In this paper, we introduce ProtoCar, a novel approach that overcomes these limitations by learning 3D vehicle prototypes from single-view images with diverse and unconstrained visual conditions. ProtoCar uses real-world driving data from LiDAR and image sensors, and employs 3D Gaussian splatting techniques to represent explicit geometric and texture. Extensive experiments demonstrate that ProtoCar generates high-quality 3D models and adapts well to various vehicle types and challenging visual scenarios, offering a scalable and effective solution for 3D modeling in environments with limited and variable visual information.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • High-Resolution Image Synthesis with Latent Diffusion Models cites Zero-Shot Text-to-Image Generation
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Perceiver: General Perception with Iterative Attention
  • Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images cites Zero-1-to-3: Zero-shot One Image to 3D Object
  • Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Zero-1-to-3: Zero-shot One Image to 3D Object cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Zero-1-to-3: Zero-shot One Image to 3D Object cites Zero-Shot Text-to-Image Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. MonoMVSNet: Monocular Priors Guided Multi-View Stereo NetworkJianfei Jiang, Qiankun Liu, Haochen Yu, Hongyuan Liu et al.ICCV 2025 · 3 citations
  2. Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World ImagesHongyuan Liu, Bochao Zou, Qiankun Liu, Haochen Yu et al.CVPR 2026 · 1 citation

Builds on24

  1. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  2. Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray et al.ICML 2021 · 6,356 citations
  3. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  4. Zero-1-to-3: Zero-shot One Image to 3D ObjectRuoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov et al.ICCV 2023 · 1,662 citations
  5. Perceiver: General Perception with Iterative AttentionAndrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals et al.ICML 2021 · 1,399 citations

Related papers

  1. SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous DrivingGeorg Hess, Carl Lindström, Maryam Fatemi, Christoffer Petersson et al.CVPR 2025
  2. RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving ScenesPou-Chun Kung, Skanda Harisha, Ram Vasudevan, Aline Eid et al.ICCV 2025 · 8 citations
  3. DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view InputQijian Tian, Xin Tan, Yuan Xie, Lizhuang MaAAAI 2025 · 45 citations
  4. Extrapolated Urban View Synthesis BenchmarkXiangyu Han, Zhen Jia, Boyi Li, Yan Wang et al.ICCV 2025 · 3 citations
  5. GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian SplattingJunzhe Jiang, Chun Gu, Yurui Chen, Li ZhangICLR 2025 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines