synsin0

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

recognize-anything

Open-source and strong foundation image recognition models.

ttt-lm-pytorch

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

ttt-lm-jax

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

SparseDrive

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

UnSAM

[NeurIPS 2024] Code release for "Segment Anything without Supervision"

XCube

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

navsim

[NeurIPS 2024] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

gru_ode_bayes

Pytorch implementation of GRU-ODE-Bayes

map4d

Photo-realistic mapping of dynamic urban areas

MagicDrive3D

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

nerf-on-the-go

[CVPR'24] NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

CarDreamer

World Model based Autonomous Driving Platform in CARLA :car:

Bench2DriveZoo

BEVFormer, UniAD, VAD in Closed-Loop CARLA Evaluation with World Model RL Expert Think2Drive

TOD3Cap

[ECCV 2024] TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

GUMP

Generative model for Unified Motion Planning tasks

BevWorld

FullySparseFusion

Fully Sparse Fusion for 3D Object Detection

LAW

Enhancing End-to-End Autonomous Driving with Latent World Model

ScatterFormer

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention (ECCV 2024)

Mask2Map

SimGen

Simulator-conditioned Driving Scene Generation

Delphi

Official Code Release of Delphi

PerlDiff

PerlDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models

Hydra-MDP

The official repository of Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation

SPIDER

SPIDER: Self-driving Planning and Intelligent Decision-making Engine with Reusability

InfDriver

Uncertainty-Guided Never-Ending Learning to Drive [CVPR 2024]

carla-aeva

Open-source simulator for autonomous driving research with Doppler Lidar plugin.