Alternatives and similar repositories for AD-GS

Users that are interested in AD-GS are comparing it to the libraries listed below

• chenhaomingbob / CSC

  View on GitHub
  [CVPR 2024] This is official implementation of our CVPR 2024 paper "Building a Strong Pre-Training Baseline for Universal 3D Large-Scale …
  ☆17Jun 11, 2024Updated last year
• cpystan / SD-VLM

  View on GitHub
  [NeurIPS 2025]《SD-VLM: Spatial Measuring and Understanding with Depth-encoded Vision Language Models》
  ☆33Dec 29, 2025Updated last month
• litwellchi / BEV-SAN

  View on GitHub
  ☆13Feb 6, 2025Updated last year
• zlichen / VectorFormer

  View on GitHub
  [ECCV 2024] This is the official implementation of Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object …
  ☆14Jul 12, 2024Updated last year
• Public-BOTs / GaussianPretrain

  View on GitHub
  GussianPretrain for Visual Pre-training in Autonomous Driving, showcasing significant improvements across various 3D perception tasks, in…
  ☆110Dec 4, 2025Updated 2 months ago
• 7uHeng / OccOoD

  View on GitHub
  Out-of-Distribution Semantic Occupancy Prediction
  ☆20Oct 22, 2025Updated 3 months ago
• fudan-zvg / DriveX

  View on GitHub
  [ICCV 2025] Driving Scene Synthesis on Free-form Trajectories with Generative Prior
  ☆39Jun 28, 2025Updated 7 months ago
• ZZY816 / VoxelSplat

  View on GitHub
  CVPR 2025: VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
  ☆73Aug 1, 2025Updated 6 months ago
• StudyingFuFu / L2COcc

  View on GitHub
  ☆22Mar 18, 2025Updated 10 months ago
• boschresearch / GaussianFlowOcc

  View on GitHub
  ☆50Oct 26, 2025Updated 3 months ago
• zuosc19 / GaussianWorld

  View on GitHub
  ☆139Dec 4, 2025Updated 2 months ago
• hustvl / PolarDETR

  View on GitHub
  ☆78Jun 23, 2022Updated 3 years ago
• chunfeng3364 / LARC

  View on GitHub
  ☆19Jun 26, 2024Updated last year
• chen-wl20 / GenWorld

  View on GitHub
  GenWorld: Towards Detecting AI-generated Real-world Simulation Videos
  ☆34Jun 13, 2025Updated 8 months ago
• lisiyao21 / Half-Physics

  View on GitHub
  Code for paper "Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions". Coming soon.
  ☆33Jul 31, 2025Updated 6 months ago
• ai4ce / EUVS-Benchmark

  View on GitHub
  [ICCV2025] Extrapolated Urban View Synthesis Benchmark
  ☆48Oct 1, 2025Updated 4 months ago
• getterupper / PreWorld

  View on GitHub
  [ICLR 2025] Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving
  ☆52Feb 14, 2025Updated last year
• BIT-XJY / EfficientOCF

  View on GitHub
  [CVPR 2025] Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
  ☆25Mar 3, 2025Updated 11 months ago
• DYZhang09 / ToC3D

  View on GitHub
  [ECCV 2024] Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression
  ☆50Sep 21, 2024Updated last year
• cancaries / SceneCrafter

  View on GitHub
  Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving
  ☆32Nov 20, 2025Updated 2 months ago
• cdb342 / ALOcc

  View on GitHub
  [ICCV 2025] ALOcc: Adaptive Lifting-based 3D Semantic Occupancy and Cost Volume-based Flow Prediction
  ☆38Dec 1, 2025Updated 2 months ago
• PKUHaoWang / EmbodiedOcc2

  View on GitHub
  [ACM MM 2025] EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler
  ☆26Aug 7, 2025Updated 6 months ago
• xtudbxk / GPSToken

  View on GitHub
  The official code for paper "GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation"
  ☆48Sep 28, 2025Updated 4 months ago
• pengxuanyang / WorldRFT

  View on GitHub
  [AAAI 2026] WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving
  ☆29Dec 23, 2025Updated last month
• ViewFormerOcc / ViewFormer-Occ

  View on GitHub
  [ECCV 2024] ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers
  ☆60Nov 1, 2024Updated last year
• WU-CVGL / Omni-Scene

  View on GitHub
  [CVPR2025] Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
  ☆237Mar 24, 2025Updated 10 months ago
• ChrisDong-THU / GaussianToken

  View on GitHub
  Official PyTorch implementation of GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting
  ☆101Apr 3, 2025Updated 10 months ago
• lzzzzzm / II-World

  View on GitHub
  [ICCV2025] II-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
  ☆172Oct 21, 2025Updated 3 months ago
• valeoai / GaussRender

  View on GitHub
  [ICCV 2025] GaussRender: Learning 3D Occupancy with Gaussian Rendering (official repository)
  ☆68Jul 7, 2025Updated 7 months ago
• BigCiLeng / bilateral-driving

  View on GitHub
  [NeurIPS 2025] Official code of Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting
  ☆143Dec 3, 2025Updated 2 months ago
• snap-research / wonderland

  View on GitHub
  ☆165Aug 13, 2025Updated 6 months ago
• wzzheng / Stag

  View on GitHub
  [ICCV 2025] Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
  ☆96Dec 10, 2024Updated last year
• gxytcrc / SGFormer

  View on GitHub
  Satellite-Ground Fusion for 3D Semantic Scene Completion
  ☆28Sep 8, 2025Updated 5 months ago
• mincheoree / BEVMap

  View on GitHub
  [WACV 2024] This is the official implementation of BEVMap, a map-aware BEV modeling framework for multiview-camera detection
  ☆21Dec 28, 2023Updated 2 years ago
• NorthSummer / SliceOcc

  View on GitHub
  ☆27Jan 27, 2025Updated last year
• hustvl / RAD

  View on GitHub
  [NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
  ☆182Nov 7, 2025Updated 3 months ago
• OpenDriveLab / LightwheelOcc

  View on GitHub
  LightwheelOcc: A 3D Occupancy Synthetic Dataset in Autonomous Driving
  ☆105Jul 2, 2025Updated 7 months ago
• V2AI / nuCraft_API

  View on GitHub
  High-res 3D Occupancy Dataset for Unified 3D Scene Understanding.
  ☆29Jul 14, 2024Updated last year
• mbjurca / RT_GS2

  View on GitHub
  This is the implementation of RT-GS2
  ☆24Oct 16, 2024Updated last year