Starred repositories
[NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
[ICRA 2024] RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision. (Former version: UniOcc)
[AAAI 2024] Official implementation of "SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation", and more.
[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
Few shot regularization for gaussian splatting
This is an official repository for "Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images"
[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.
[CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
[CVPR 2023] Virtual Occlusions Through Implicit Depth
Official PyTorch Implementation of the CVPR23 Paper "DINER: Depth-aware Image-based NEural Radiance fields"
Extended LaTeX template for CVPR/ICCV papers
Code of "OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments".
[CVPR24] COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
[CVPR 2024] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications
Vision-based 3D occupancy prediction in autonomous driving: a review and outlook
[CVPR 2024 Oral, Best Paper Award Candidate] Official repository of "PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness"
[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction
Resources for the IGARSS 2024 Tutorial "Data-Efficient Deep Learning for EO"
PyTorch Implementation of introducing diffusion approach to 3D depth perception ECCV 2024
Park et al., Non-Local Spatial Propagation Network for Depth Completion, ECCV, 2020
SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]
Official implementation of the paper: Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023)
A latent text-to-image diffusion model
[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving