Image Segmentation - Paper Copilot

The Relightables: Volumetric Performance Capture of Humans with Realistic Relighting

Kaiwen Guo, Peter Lincoln, Philip Davidson, Jay Busch, Xueming Yu, Matt Whalen, Geoff Harvey, Sergio Orts-Escolano, Rohit Pandey, Jason Dourgarian, Matthew DuVall, Danhang Tang, Anastasia Tkach, Adarsh Kowdle, Emily Cooper, Mingsong Dou, Sean Fanello, Graham Fyffe, Christoph Rhemann, Jonathan Taylor, Paul Debevec, and Shahram Izadi

Google

Portals

Abstract

We present "The Relightables", a volumetric capture system for photorealistic and high quality relightable full-body performance capture. While significant progress has been made on volumetric capture systems, focusing on 3D geometric reconstruction with high resolution textures, much less work has been done to recover photometric properties needed for relighting. Results from such systems lack high-frequency details and the subject's shading is prebaked into the texture. In contrast, a large body of work has addressed relightable acquisition for image-based approaches, which photograph the subject under a set of basis lighting conditions and recombine the images to show the subject as they would appear in a target lighting environment. However, to date, these approaches have not been adapted for use in the context of a high-resolution volumetric capture system. Our method combines this ability to realistically relight humans for arbitrary environments, with the benefits of free-viewpoint volumetric capture and new levels of geometric accuracy for dynamic performances. Our subjects are recorded inside a custom geodesic sphere outfitted with 331 custom color LED lights, an array of high-resolution cameras, and a set of custom high-resolution depth sensors. Our system innovates in multiple areas: First, we designed a novel active depth sensor to capture 12.4MP depth maps, which we describe in detail. Second, we show how to design a hybrid geometric and machine learning reconstruction pipeline to process the high resolution input and output a volumetric video. Third, we generate temporally consistent reflectance maps for dynamic performers by leveraging the information contained in two alternating color gradient illumination images acquired at 60Hz. Multiple experiments, comparisons, and applications show that The Relightables significantly improves upon the level of realism in placing volumetrically captured human performances into arbitrary CG scenes.

Related Works

Image-based Rendering; Model Based; Volumetric Capture; Machine Learning

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, Jianming Liang

Arizona State University

Portals

Abstract

In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at reducing the semantic gap between the feature maps of the encoder and decoder sub-networks. We argue that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar. We have evaluated UNet++ in comparison with U-Net and wide U-Net architectures across multiple medical image segmentation tasks: nodule segmentation in the low-dose CT scans of chest, nuclei segmentation in the microscopy images, liver segmentation in abdominal CT scans, and polyp segmentation in colonoscopy videos. Our experiments demonstrate that UNet++ with deep supervision achieves an average IoU gain of 3.9 and 3.4 points over U-Net and wide U-Net, respectively.

Segment Anything

Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Doll

Meta AI Research, FAIR

Portals

Abstract

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at https://segment-anything.com to foster research into foundation models for computer vision.

LSeg: Language-driven Semantic Segmentation

Boyi Li, Kilian Q. Weinberger, Serge Belongie, Vladlen Koltun, Ren

Cornell University; University of Copenhagen; Apple; Intel Labs

Portals

Abstract

We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that computes dense per-pixel embeddings of the input image. The image encoder is trained with a contrastive objective to align pixel embeddings to the text embedding of the corresponding semantic class. The text embeddings provide a flexible label representation in which semantically similar labels map to similar regions in the embedding space (e.g., "cat" and "furry"). This allows LSeg to generalize to previously unseen categories at test time, without retraining or even requiring a single additional training sample. We demonstrate that our approach achieves highly competitive zero-shot performance compared to existing zero- and few-shot semantic segmentation methods, and even matches the accuracy of traditional segmentation algorithms when a fixed label set is provided. Code and demo are available at https://github.com/isl-org/lang-seg.

Highly Accurate Dichotomous Image Segmentation

Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, Luc Van Gool

MBZUAI; TUM; ETH Zurich; Terminus Group

Portals

Abstract

We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images. To this end, we collected the first large-scale DIS dataset, called DIS5K, which contains 5,470 high-resolution (e.g., 2K, 4K or larger) images covering camouflaged, salient, or meticulous objects in various backgrounds. DIS is annotated with extremely fine-grained labels. Besides, we introduce a simple intermediate supervision baseline (IS-Net) using both feature-level and mask-level guidance for DIS model training. IS-Net outperforms various cutting-edge baselines on the proposed DIS5K, making it a general self-learned supervision network that can facilitate future research in DIS. Further, we design a new metric called human correction efforts (HCE) which approximates the number of mouse clicking operations required to correct the false positives and false negatives. HCE is utilized to measure the gap between models and real-world applications and thus can complement existing metrics. Finally, we conduct the largest-scale benchmark, evaluating 16 representative segmentation models, providing a more insightful discussion regarding object complexities, and showing several potential applications (e.g., background removal, art design, 3D reconstruction). Hoping these efforts can open up promising directions for both academic and industries. Project page: https://xuebinqin.github.io/dis/index.html.

A Survey: Image and Video Matting

Jue Wang, Michael F. Cohen

Adobe Systems; Microsoft Research

Portals

Abstract

Matting refers to the problem of accurate foreground estimation in images and video. It is one of the key techniques in many image editing and film production applications, thus has been extensively studied in the literature. With the recent advances of digital cameras, using matting techniques to create novel composites or facilitate other editing tasks has gained increasing interest from both professionals as well as consumers. Consequently, various matting techniques and systems have been proposed to try to efficiently extract high quality mattes from both still images and video sequences. This survey provides a comprehensive review of existing image and video matting algorithms and systems, with an emphasis on the advanced techniques that have been recently proposed. The first part of the survey is focused on image matting. The fundamental techniques shared by many image matting algorithms, such as color sampling methods and matting affinities, are first analyzed. Image matting techniques are then classified into three categories based on their underlying methodologies, and an objective evaluation is conducted to reveal the advantages and disadvantages of each category. A unique Accuracy vs. Cost analysis is presented as a practical guidance for readers to properly choose matting tools that best fit their specific requirements and constraints. The second part of the survey is focused on video matting. The difficulties and challenges of video matting are first analyzed, and various ways of combining matting algorithms with other video processing techniques for building efficient video matting systems are reviewed. Key contributions, advantages as well as limitations of important systems are summarized. Finally, special matting systems that rely on capturing additional foreground/background information to automate the matting process are discussed. A few interesting directions for future matting research are presented in the conclusion.

PyMatting: A Python Library for Alpha Matting

Thomas Germer, Tobias Uelwer, Stefan Conrad, Stefan Harmeling

Heinrich-Heine-Universit¨at D¨usseldorf

Portals

Abstract

An important step of many image editing tasks is to extract specific objects from an image in order to place them in a scene of a movie or compose them onto another background. Alpha matting describes the problem of separating the objects in the foreground from the background of an image given only a rough sketch. We introduce the PyMatting package for Python which implements various approaches to solve the alpha matting problem. Our toolbox is also able to extract the foreground of an image given the alpha matte. The implementation aims to be computationally efficient and easy to use. The source code of PyMatting is available under an open-source license at https://github.com/pymatting/pymatting.

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane, Martin Jagersand

University of Alberta

Portals

Abstract

In this paper, we design a simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD). The architecture of our U2-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U2-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U2-Net† (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets.

Related Works

Multi-level deep feature integration; Multi-scale feature extraction

AlphaGAN: Generative adversarial networks for natural image matting

Sebastian Lutz, Konstantinos Amplianitis, Aljosa Smolic

Trinity College Dublin

Portals

Abstract

We present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition of the adversarial loss from the discriminator that is trained to classify well-composited images. Further, we improve existing encoder-decoder architectures to better deal with the spatial localization issues inherited in convolutional neural networks (CNN) by using dilated convolutions to capture global context information without downscaling feature maps and losing spatial information. We present state-of-the-art results on the alphamatting online benchmark for the gradient error and give comparable results in others. Our method is particularly well suited for fine structures like hair, which is of great importance in practical matting applications, e.g. in film/TV production.

Related Works

Local sample-based natural image matting; Deep learning in natural image matting

Category: Image Segmentation

Portals

Abstract

Related Works

Portals

Abstract

Portals

Abstract

Portals

Abstract

Portals

Abstract

Portals

Abstract

Portals

Abstract

Portals

Abstract

Related Works

Portals

Abstract

Related Works