ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

11/19/2021
by   Laurynas Karazija, et al.
3

There has been a recent surge in methods that aim to decompose and segment scenes into multiple objects in an unsupervised manner, i.e., unsupervised multi-object segmentation. Performing such a task is a long-standing goal of computer vision, offering to unlock object-level reasoning without requiring dense annotations to train segmentation models. Despite significant progress, current models are developed and trained on visually simple scenes depicting mono-colored objects on plain backgrounds. The natural world, however, is visually complex with confounding aspects such as diverse textures and complicated lighting effects. In this study, we present a new benchmark called ClevrTex, designed as the next challenge to compare, evaluate and analyze algorithms. ClevrTex features synthetic scenes with diverse shapes, textures and photo-mapped materials, created using physically based rendering techniques. It includes 50k examples depicting 3-10 objects arranged on a background, created using a catalog of 60 materials, and a further test set featuring 10k images created using 25 different materials. We benchmark a large set of recent unsupervised multi-object segmentation models on ClevrTex and find all state-of-the-art approaches fail to learn good representations in the textured setting, despite impressive performance on simpler data. We also create variants of the ClevrTex dataset, controlling for different aspects of scene complexity, and probe current approaches for individual shortcomings. Dataset and code are available at https://www.robots.ox.ac.uk/ vgg/research/clevrtex.

READ FULL TEXT

page 4

page 7

page 9

page 22

page 23

page 24

page 25

page 26

research
02/09/2019

Photorealistic Image Synthesis for Object Instance Detection

We present an approach to synthesize highly photorealistic images of 3D ...
research
06/16/2023

OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning

Humans possess the cognitive ability to comprehend scenes in a compositi...
research
05/31/2021

APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation

Recent advances in unsupervised learning for object detection, segmentat...
research
04/06/2023

LANe: Lighting-Aware Neural Fields for Compositional Scene Synthesis

Neural fields have recently enjoyed great success in representing and re...
research
11/18/2022

Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenes

We present a multi-view inverse rendering method for large-scale real-wo...
research
03/18/2022

Discovering Objects that Can Move

This paper studies the problem of object discovery – separating objects ...
research
12/08/2022

Phone2Proc: Bringing Robust Robots Into Our Chaotic World

Training embodied agents in simulation has become mainstream for the emb...

Please sign up or login with your details

Forgot password? Click here to reset