Self-Supervised LiDAR Ground Segmentation [CVPR 2026]

CVPR 2026 论文和开源项目合集

[CVPR 2025] PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding

The source code for "A novel projection map driven multimodal fusion framework for ALS point cloud segmentation"

[CVPR 2026 Oral] Official implementation of OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective

VMamba: Visual State Space Models，code is based on mamba

Reference PyTorch implementation and models for DINOv3

[RA-L 2023] CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic Segmentation

OMNIMAMBA: A Mamba-Driven Integrated Framework for Effective and Efficient Point Cloud Analysis

[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion

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

[ICRA'24 Best UAV Paper Award Finalist] An Efficient Global Planner for Aerial Coverage

[NeurIPS2024] Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

Code Implementation of EfficientVMamba

[NeurIPS 2024] Official implementation of MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection.

[WACV 2025] Python implementation of Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation

Official repo for EAMamba: Efficient All-Around Vision State Space Model for Image Restoration.

[ICLR2025] Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion

[CVPR 2025] SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures

[CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)

[NeurIPS 2024] PointMamba: A Simple State Space Model for Point Cloud Analysis

Exploring Token Serialization for Mamba-based LiDAR Point Cloud Segmentation

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

[IJCV] PointSegBase: a codebase for point cloud segmentation research. Related works: Deep Hierarchical Learning for 3D Semantic Segmentation

Segmentator for clustering on meshes or pointclouds

[ICCV2025] All in One: Visual-Description-Guided Unified Point Cloud Segmentation