paper-with-me

Papers

pix2gestalt: Amodal Segmentation by Synthesizing Wholes

2024-01-25 · CVPR 2024 1 · Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, Carl Vondrick

We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind occlusions. By capitalizing on large-scale diffusion models and transferring their representations to this task, we learn a conditional diffusion model for reconstructing whole objects in challenging zero-shot cases, including examples that break natural and physical priors, such as art. As training data, we use a synthetically curated dataset containing occluded objects paired with their whole counterparts. Experiments show that our approach outperforms supervised baselines on established benchmarks. Our model can furthermore be used to significantly improve the performance of existing object recognition and 3D reconstruction methods in the presence of occlusions.

📄 PDF Abstract BibTeX arXiv:2401.14398

Code (1)

cvlab-columbia/pix2gestalt 공식 구현 pytorch

Tasks

3D ReconstructionObject RecognitionSegmentation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Finding Closure: A Closer Look at the Gestalt Law of Closure in Convolutional Neural Networks

2024-08-22 · Yuyan Zhang, Derya Soydaner, Lisa Koßmann, Fatemeh Behrad 외

The human brain has an inherent ability to fill in gaps to perceive figures as complete wholes, even when parts are missing or fragmented. This phenomenon is known as Closure in psychology, one of the Gestalt laws of per…

Object Recognition

Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation

2018-04-24 · Patrick Follmann, Rebecca König, Philipp Härtinger, Michael Klostermann

Semantic amodal segmentation is a recently proposed extension to instance-aware segmentation that includes the prediction of the invisible region of each object instance. We present the first all-in-one end-to-end traina…

Amodal Instance SegmentationData AugmentationInstance SegmentationSegmentation+1

Foundation Models for Amodal Video Instance Segmentation in Automated Driving

2024-09-21 · Jasmin Breitenstein, Franz Jünger, Andreas Bär, Tim Fingscheidt

In this work, we study amodal video instance segmentation for automated driving. Previous works perform amodal video instance segmentation relying on methods trained on entirely labeled video data with techniques borrowe…

Amodal Instance SegmentationInstance SegmentationPoint TrackingSegmentation+2

Amodal Ground Truth and Completion in the Wild

2023-12-28 · CVPR 2024 1 · Guanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman

This paper studies amodal image segmentation: predicting entire object segmentation masks including both visible and invisible (occluded) parts. In previous work, the amodal segmentation ground truth on real images is us…

Image SegmentationSegmentationSemantic Segmentation

Coarse-to-Fine Amodal Segmentation with Shape Prior

2023-08-31 · ICCV 2023 1 · Jianxiong Gao, Xuelin Qian, Yikai Wang, Tianjun Xiao 외

Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addre…

ObjectSegmentationSemantic Segmentation