VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Official PyTorch implementation of D^2-World as the second place of CVPR 2024 Predictive World Model Challenge.

Reasoning 3D Segmentation - "segment anything"/grounding/part seperation in 3D with natural conversations.

DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

[CVPR 2024 Oral, Best Paper Award Candidate] Official repository of "PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness"

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

Open-Sora: Democratizing Efficient Video Production for All

[CVPR'24] DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

The official PyTorch implementation of Google's Gemma models

(AAAI2024) Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

A curated list of awesome world models for autonomous driving (continually updated)

A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

[ECCV 2024] 3D World Model for Autonomous Driving

[ICRA 2024] RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision. (Former version: UniOcc)

Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)

A series of large language models trained from scratch by developers @01-ai

A JAX-based simulator for autonomous driving research.

[ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

Talk2BEV: Language-Enhanced Bird's Eye View Maps (Accepted to ICRA'24)

An Invitation to 3D Vision: A Tutorial for Everyone

Web-based 3D visualization + Python

Meta-Transformer for Unified Multimodal Learning

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation