[CVPR 2026 Highlight] LitePT: Lighter Yet Stronger Point Transformer

Self-Supervised LiDAR Ground Segmentation [CVPR 2026]

📄 Easily create your resume with Markdown on VSCode / Typora / Obsidian

[IEEE IROS 2024]InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

Robust and Efficient Occupancy Prediction

[ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"

[ICCV2023 Oral] LATR: 3D Lane Detection from Monocular Images with Transformer

[ECCV'24] Online Vectorized HD Map Construction using Geometry

🔥(ECCV 2024 Oral) RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation

[ICRA 2024] VeloVox: A Low-Cost and Accurate 4D Object Detector with Single-Frame Point Cloud of Livox LiDAR

[IEEE RA-L] Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction

[NeurIPS'24 Spotlight] Is Your LiDAR Placement Optimized for 3D Scene Understanding?

[WACV 2025 Oral] Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding

This is the official implementation of "LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels" (Accepted at CVPR 2024).

Official Repo For IEEE RAL 2024 Accepted paper "Fast-Poly"

[ACCV 2024] Simple, Easy 3D Object Detection with Point-Wise Semantics

[ICRA'2024] MonoOcc: Digging into Monocular Semantic Occupancy Prediction

[CVPR 2024] The official implementation for "SemCity: Semantic Scene Generation with Triplane Diffusion"

[CVPR 2024, highlight] Dynamic LiDAR Re-simulation using Compositional Neural Fields

Point Could Mamba: Point Cloud Learning via State Space Model

The Official Implementation of PillarNeSt

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

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)

[CVPR'24] Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

Official project repository of AVS-Net