Official implementation of "LidarDM: Generative LiDAR Simulation in a Generated World" (ICRA 2025)

Collect some World Models for Autonomous Driving (and Robotic) papers.

a comprehensive and critical synthesis of the emerging role of GenAI across the full autonomous driving stack

[CoRL 2022] SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation

PlantDreamer: Achieving Realistic 3D Plant Models with Diffusion-Guided Gaussian Splatting [CVPPA: ICCVW 2025]

[CVPR 2025] FLAIR: VLM with Fine-grained Language-informed Image Representations

🌐 3D and 4D World Modeling: A Survey

Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

[NeurIPS 2024 Spotlight] PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

[ECCV 2024] Official Implementation of the paper "HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects"

Papers and Datasets about Point Cloud.

[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation

🐧 A list of awesome Point Cloud Generation papers

SPVD: Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models

An autoregressive model for point cloud generation augmented with self-attention

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

3D adaptive binary space partitioning and beyond

[CVPR 2025] Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

Implementation of the CVPR2025 paper "SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation"

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

This is the official code for the CVPR 2024 Publication: Tiger: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process

An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.

Parametric completion for polygonal surface reconstruction [CVPR 2025]

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

Official Implementation of "Instance Segmentation of Scene Sketches Using Natural Image Priors" (SIGGRAPH 2025)

Official Implementation for Fast Point Cloud Generation with Straight Flows

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM