semantic-scene-completion

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

[ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

Maybe the first academic open work on stereo 3D SSC method with vision-only input.

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion (AAAI 2021)

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

[IROS2024] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

[CVPR 2024] Symphonies (Scene-from-Insts): Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

Semantic Scene Completion

[IJCAI 2024]Official PyTorch Implementation of Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion

Implement some state-of-the-art methods of Semantic Scene Completion (SSC) task in PyTorch. [1] 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior (CVPR 2020)

[ECCV 2024] Monocular Occupancy Prediction for Scalable Indoor Scenes

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion (ICCV 2025)

[CVPR 2024] Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles

[ECCV 2024]Official PyTorch Implementation of HTCL : Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion

[ArXiv 25] VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection

[NeurIPS 2024] TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight

[ICRA 2024] SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net

This is a PyTorch implementation of a Bayesian Convolutional Neural Network (BCNN) for Semantic Scene Completion on the SUNCG dataset. Given a depth image the network outputs a semantic segmentation and entropy score in 3D voxel format.