autonomousvision

sdfstudio

A Unified Framework for Surface Reconstruction

transfuser

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

mip-splatting

[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

unimatch

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

stylegan-xl

[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

gaussian-opacity-fields

[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

projected-gan

[NeurIPS'21] Projected GANs Converge Faster

convolutional_occupancy_networks

[ECCV'20] Convolutional Occupancy Networks

navsim

[CoRL '25] Pseudo-Simulation for Autonomous Driving; [NeurIPS '24] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

tuplan_garage

[CoRL'23] Parting with Misconceptions about Learning-based Vehicle Motion Planning

carla_garage

[ICCV'23] Hidden Biases of End-to-End Driving Models & A starter kit for the CARLA leaderboard 2.0.

kitti360Scripts

This repository contains utility scripts for the KITTI-360 dataset.

unisurf

[ICCV'21] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

LaRa

[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model

plant

[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations

factor-fields

[SIGGRAPH 2023] We provide a unified formula for neural fields (Factor Fields) and a novel dictionary factorization (Dictionary Fields)

sledge

[ECCV'24] SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

gta

[ICLR'24] GTA: A Geometry-Aware Attention Mechanism for Multi-view Transformers

kitti360LabelTool

murf

[CVPR'24] MuRF: Multi-Baseline Radiance Fields

akorn

[ICLR'25] Artificial Kuramoto Oscillatory Neurons

CaRL

[CoRL 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards

volsurfs

[CVPR 2025] Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

mdpo

MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models

mvdatasets

Standardized DataLoaders for 3D Computer Vision

carla_route_generator

autonomousvision.github.io

Blog of the Autonomous Vision Group at MPI-IS Tübingen and University of Tübingen.

ppo.cpp

hdt

[COLM'24] HDT: Hierarchical Document Transformer

pritti