InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

ARCH2S: Dataset and Benchmark for Learning Exterior Architectural Structures from Point Clouds (CVPRW 2024, Oral)

Official implementation of the paper A-Scan2BIM: Assistive Scan to Building Information Modeling

Python package for 3D geometry CAD/BIM/CAM

Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.

Official repository for paper "Attention-based Point Cloud Edge Sampling" (APES), Highlight@CVPR 2023

Official implementation of "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding" (CVPR, 2022)

Kernel Point Convolution implemented in PyTorch

[ECCV 2022] Official pytorch implementation of the paper, "PointMixer: MLP-Mixer for Point Cloud Understanding"

An All-MLP solution for Vision, from Google AI

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

[AAAI 2024-Oral] EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder

[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

Pytorch kernels for spatial operations on point clouds

BoW Pooling: A Plug-and-Play Unit for Feature Aggregation of Point Clouds (AAAI2021)

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

[NeurIPS 2023] PointGPT: Auto-regressively Generative Pre-training from Point Clouds

ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model, a unified and user-friendly shape-language model

[ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation (NeurIPS 2023)

Contrastive Boundary Learning for Point Cloud Segmentation (CVPR2022)

Official pytorch implementation of TopoSeg: Topology-Aware Nuclear Instance Segmentation The code will be available soon!

Official pytorch implementation of TopoSeg: Topology-Aware Nuclear Instance Segmentation

Topological losses for spatially coherent CNN-based (multi-class) image segmentation in 2D and 3D

Kernel Point Convolutions

[NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies