paper-with-me

Papers

Conditional Reconstruction for Open-set Semantic Segmentation

2022-03-02 · Ian Nunes, Matheus B. Pereira, Hugo Oliveira, Jefersson A. dos Santos, Marcus Poggi

Open set segmentation is a relatively new and unexploredtask, with just a handful of methods proposed to model suchtasks.We propose a novel method called CoReSeg thattackles the issue using class conditional reconstruction ofthe input images according to their pixelwise mask. Ourmethod conditions each input pixel to all known classes,expecting higher errors for pixels of unknown classes. Itwas observed that the proposed method produces better se-mantic consistency in its predictions, resulting in cleanersegmentation maps that better fit object boundaries. CoRe-Seg outperforms state-of-the-art methods on the Vaihin-gen and Potsdam ISPRS datasets, while also being com-petitive on the Houston 2018 IEEE GRSS Data Fusiondataset. Official implementation for CoReSeg is availableat:https://github.com/iannunes/CoReSeg.

📄 PDF Abstract BibTeX arXiv:2203.01368

Code (1)

iannunes/coreseg 공식 구현 pytorch

Tasks

Semantic Segmentation

Similar Papers 제목 키워드 기반

Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos

2025-07-29 · Ziren Gong, Xiaohan Li, Fabio Tosi, Jiawei Han 외 arxiv

We present Ov3R, a novel framework for open-vocabulary semantic 3D reconstruction from RGB video streams, designed to advance Spatial AI. The system features two key components: CLIP3R, a CLIP-informed 3D reconstruction …

3D Reconstruction

Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Results

2025-05-09 · Wang Fang, Shirin Rahimi, Olivia Bennett, Sophie Carter 외

Point-cloud semantic segmentation underpins a wide range of critical applications. Although recent deep architectures and large-scale datasets have driven impressive closed-set performance, these models struggle to recog…

SegmentationSemantic Segmentation

Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks

2023-05-10 · Olaf Wysocki, Yan Xia, Magdalena Wysocki, Eleonora Grilli 외

Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing challenge. Unlike mesh-based models, they require watertight geometry and object-wise semantics at the fa\c{c}ade level. The pr…

3D ReconstructionAutonomous DrivingSegmentationSemantic Segmentation

Real-time Progressive 3D Semantic Segmentation for Indoor Scene

2018-04-01 · Quang-Hieu Pham, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung

The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for…

3D Semantic SegmentationClusteringScene SegmentationSegmentation+1

PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction

2024-07-01 · Xuan Yu, Yili Liu, Chenrui Han, Sitong Mao 외

Panoptic reconstruction is a challenging task in 3D scene understanding. However, most existing methods heavily rely on pre-trained semantic segmentation models and known 3D object bounding boxes for 3D panoptic segmenta…

3D Panoptic SegmentationInstance SegmentationPanoptic SegmentationScene Understanding+3