paper-with-me

홈 › Papers

Instance-wise Occlusion and Depth Orders in Natural Scenes

2021-11-29 · CVPR 2022 1 · Hyunmin Lee, Jaesik Park

In this paper, we introduce a new dataset, named InstaOrder, that can be used to understand the geometrical relationships of instances in an image. The dataset consists of 2.9M annotations of geometric orderings for class-labeled instances in 101K natural scenes. The scenes were annotated by 3,659 crowd-workers regarding (1) occlusion order that identifies occluder/occludee and (2) depth order that describes ordinal relations that consider relative distance from the camera. The dataset provides joint annotation of two kinds of orderings for the same instances, and we discover that the occlusion order and depth order are complementary. We also introduce a geometric order prediction network called InstaOrderNet, which is superior to state-of-the-art approaches. Moreover, we propose a dense depth prediction network called InstaDepthNet that uses auxiliary geometric order loss to boost the accuracy of the state-of-the-art depth prediction approach, MiDaS [56].

📄 PDF Abstract BibTeX arXiv:2111.14562

Code (1)

POSTECH-CVLab/InstaOrder 공식 구현 pytorch

Tasks

Depth EstimationDepth PredictionPredictionScene Understanding

Similar Papers 제목 키워드 기반

USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks

2022-07-15 · Johan Vertens, Wolfram Burgard

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework l…

Motion EstimationOptical Flow Estimation

Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers

2026-03-06 · Ruidong Chen, Yancheng Bai, Xuanpu Zhang, Jianhao Zeng 외 arxiv

Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations: (i) training-based approaches inherit data bias and often degrade image quality, and (ii) cu…

Text-to-Image Generation

Occlusion-Ordered Semantic Instance Segmentation

2025-04-18 · Soroosh Baselizadeh, Cheuk-To Yu, Olga Veksler, Yuri Boykov

Standard semantic instance segmentation provides useful, but inherently 2D information from a single image. To enable 3D analysis, one usually integrates absolute monocular depth estimation with instance segmentation. Ho…

Depth EstimationInstance SegmentationMonocular Depth EstimationSegmentation+1

Revisiting Depth Layers from Occlusions

2013-06-01 · CVPR 2013 6 · Adarsh Kowdle, Andrew Gallagher, Tsuhan Chen

In this work, we consider images of a scene with a moving object captured by a static camera. As the object (human or otherwise) moves about the scene, it reveals pairwise depth-ordering or occlusion cues. The goal of th…

Object

Holistic Order Prediction in Natural Scenes

2025-10-02 · Pierre Musacchio, Hyunmin Lee, Jaesik Park arxiv

Even in controlled settings, understanding instance-wise geometries is a challenging task for a wide range of visual models. Although specialized systems exist, modern arts rely on expensive input formats (category label…