The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

(ICLR 2025) The official pytorch implementation of "UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation"

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Pytorch code for NeurIPS-20 Paper "Object Goal Navigation using Goal-Oriented Semantic Exploration"

[IROS '24] Volumetric Mapping with Panoptic Refinement using Kernel Density Estimation for Mobile Robots

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

PanopticNDT: Efficient and Robust Panoptic Mapping

[IROS2024]DHP-Mapping: A Dense Panoptic Mapping System with Hierarchical World Representation and Label Optimization Techniques

A library for flexible voxel-based mapping, mainly focusing on truncated and Euclidean signed distance fields.

A flexible submap-based framework towards spatio-temporally consistent volumetric mapping and scene understanding.

Multi-resolution panoptic volumetric mapingp using Voxfield as its mapping backbone [IROS' 22]

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.