[ICCV 2025] GaussRender: Learning 3D Occupancy with Gaussian Rendering (official repository)

【ICML 2026】GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

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

CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation

Masked Depth Modeling for Spatial Perception

Code of "OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments".

[CoRL2024] Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction

Ping Viewer is an open-source application to view and record data from the Blue Robotics Ping Echosounder and Ping360 Scanning Sonar.

CUDA accelerated rasterization of gaussian splatting

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

[CVPR 2026] Test-Time 3D Occupancy Prediction

[CVPR2026 Oral, Award Candidate] Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes

[ICLR 2025] DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

[ICCV 2025] ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

ZipSplat: Fewer Gaussians, Better Splats

[CVPR 2026] An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving

[AAAI 2025] ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder

OPUS: Occupancy Prediction Using a Sparse Set

CVPR 2025: VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction

[CVPR2026] Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction

[RSS 2026] FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction

[ICCV 2025] Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

[CVPR 2024] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications

[CVPR26] ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction

Unsupervised single image depth prediction with CNNs

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Spatial Sparse Convolution Library