Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-10

Scene Segmentation

3260 papers • 126 benchmarks • 313 datasets

Scene segmentation is the task of splitting a scene into its various object components. Image adapted from Temporally coherent 4D reconstruction of complex dynamic scenes.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in scene-segmentation-10

Trend

Dataset

Best Model

Actions

SUN-RGBD

SUN-RGBD

ScanNet

ScanNet

StreetHazards

StreetHazards

Libraries

i

Use these libraries to find scene-segmentation-10 models and implementations

PaddlePaddle/PaddleSeg

3 papers 8,196

Datasets

ScanNet

NYUv2

SUN RGB-D

UAVid

StreetHazards

Mila Simulated Floods

Mila Simulated Floods

Subtasks

Thermal Image Segmentation

Most implemented papers

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

C. Qi, Hao Su, Kaichun Mo, L. Guibas•Thu Dec 01 2016

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

16162

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

NYU Depth v2

NYU Depth v2

UAVid

UAVid

3 papers 2,915

isl-org/Open3D-ML

3 papers 1,644

open-mmlab/mmsegmentation

2 papers 7,316

JanMarcelKezmann/TensorFlow-Advance…

2 papers 149

lalithjets/global-reasoned-multi-ta…

2 papers 11

Berkeley DeepDrive Video

Berkeley DeepDrive Video

0

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Alex Kendall, Vijay Badrinarayanan, R. Cipolla•Sun Nov 01 2015

Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet.

17098 0

Fully convolutional networks for semantic segmentation

Evan Shelhamer, Trevor Darrell, Jonathan Long•Thu Nov 13 2014

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

40974 0

Point Transformer

Nico Engel, Vasileios Belagiannis, K. Dietmayer•Sun Nov 01 2020

This work proposes SortNet, as part of the Point Transformer, which induces input permutation invariance by selecting points based on a learned score, to extract local and global features and relate both representations by introducing the local-global attention mechanism.

2509 0

Panoptic Segmentation

Kaiming He, Ross B. Girshick, C. Rother, Piotr Dollár, Alexander Kirillov•Tue Jan 02 2018

A novel panoptic quality (PQ) metric is proposed that captures performance for all classes (stuff and things) in an interpretable and unified manner and is performed a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task.

1586 0

Dual Attention Network for Scene Segmentation

J. Fu, J. Liu, Haijie Tian, Zhiwei Fang, Hanqing Lu•Sat Sep 08 2018

New state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset is achieved without using coarse data.

5845 0

KPConv: Flexible and Deformable Convolution for Point Clouds

C. Qi, L. Guibas, Jean-Emmanuel Deschaud, F. Goulette, Hugues Thomas, B. Marcotegui•Wed Apr 17 2019

KPConv is a new design of point convolution, i.e. that operates on point clouds without any intermediate representation, that outperform state-of-the-art classification and segmentation approaches on several datasets.

3040 0

Seamless Scene Segmentation

P. Kontschieder, S. R. Bulò, L. Porzi, Aleksander Colovic•Thu May 02 2019

This work introduces a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results by means of a panoptic output format, going beyond the simple combination of independently trained segmentation and detection models.

224 0

Point-Voxel CNN for Efficient 3D Deep Learning

Zhijian Liu, Haotian Tang, Yujun Lin, Song Han•Sun Jul 07 2019

This paper proposes PVCNN that represents the 3D input data in points to reduce the memory consumption, while performing the convolutions in voxels to largely reduce the irregular data access and improve the locality.

773 0

Adding a benchmark result helps the community track progress.

Scene Segmentation | State-of-the-Art