Lilac-Lee

dust3r

DUSt3R: Geometric 3D Vision Made Easy

Segment-Any-Point-Cloud

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

SpaTracker

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

efficient-kan

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

pykan

Kolmogorov Arnold Networks

ScatterFormer

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention (ECCV 2024)

performer-pytorch

An implementation of Performer, a linear attention-based transformer, in Pytorch

DiJiang

[ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear attention mechanism.

structured_init

Structured Initialization for Attention in Vision Transformers

FastKernelSF

Fast per-point embedding kernel for scene flow estimation

Depth-Anything

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

mamba

Mamba SSM architecture

Exphormer

Exphormer: Sparse Transformer for Graphs

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Dynamic3DGaussians

impulse_init

Convolutional Initialization for Data-Efficient Vision Transformers

segment-anything-fast

A batched offline inference oriented version of segment-anything

MBNSF

[3DV 2024] Repository for "Multi-Body Neural Scene Flow", in International Conference on 3D Vision 2024.

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

open-interpreter

A natural language interface for computers

RobustPPE

Robust Point Cloud Processing through Positional Embedding

keops

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

falkon

Large-scale, multi-GPU capable, kernel solver

NKSR

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

OpenPCDet

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

omnimotion

FastNSF

Fast Neural Scene Flow (ICCV 2023)

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

RVSS_Need4Speed

compressive_benchmark

This repo contains the released version of code and datasets used for our IROS 2021 paper: "Map Compressibility Assessment for LiDAR Registration.