Pushing the Limits for View Prediction in Video Coding

Ogniewski, Jens; Forssén, Per-Erik

doi:10.5220/0006131500680076

Cited by 4 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our method, we instead render the point sets into synthetic images with a splatting technique [105,84]. Splatting can be processed in image space, enabling efficient and easily parallelizable implementations.…”

Section: Point Set Renderingmentioning

confidence: 99%

Learning Representations for Segmentation and Registration

Lawin

2021

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

I could not have made it through my Ph.D. studies without the help of my colleagues at CVL. First and foremost I would like to thank my supervisor Per-Erik Forssén for his friendliness and all the valuable guidance. Throughout, he has always been encouraging and open to discuss ideas. I have also enjoyed our supervision meetings, and often certain information has come to light during our discussions. Next, I want to thank my co-supervisor Michael Felsberg who first took me in as a Ph.D. student, or should I say, tricked me into it. Either way, I am glad that he gave me the chance at perusing a Ph.D. degree. I am very thankful for his support and for learning from his knowledge and experience. To both my supervisors I want to express my gratitude for giving me the freedom and the encouragement to explore different topics and ideas. I also want to thank all my collaborators and co-authors for sharing their brilliant ideas and for our interesting discussions. Martin Danelljan for his notation, for inviting me into exciting research projects and for pushing me into taking time-consuming math courses. Fahad Shahbaz Khan for his encouraging attitude and spreading of positive energy during the darkest deadline hours. Andreas Robinson for sharing his programming skills and for patiently helping me with software installations and computer issues. Goutam Bhat for his awesome figures, ability to improve the results and our discussions on football. I am very proud of what we achieved in our joint works. Moreover, I want to thank all of CVL, including past and current members, for the friendly atmosphere at the lab and all the interesting discussions during coffee breaks. I further want to thank Zahra for arranging barbecues and Mikael for hosting board gaming sessions. Hannes, Abdo and Emanuel for their nice company while sharing offices with me. I am also grateful to everyone who joined me for late lunch, even if the only acceptable option was the bad house. Special thanks go to Per-Erik, Gustav, Abdo, and Andreas for helping out with the proofreading of the thesis manuscript. Lastly, I want to thank my family and all my friends for all the support and good times.

show abstract

Section: Point Set Renderingmentioning

confidence: 99%

Learning Representations for Segmentation and Registration

Lawin

2021

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

show abstract

“…Similar to the method proposed in [19], we perform mean-shift clustering [24] of the projected points in each pixel with respect to the depth z i weighted with w i,j using a Gaussian kernel density estimator G(d, s 2 ), where s 2 denotes the kernel width. Starting from the depth value d 0 i = z i for each point i ∈ I j that contributes to the current pixel j, I j = {i : p j − y i < r}, the following expression is iterated until convergence…”

Section: Render Viewsmentioning

confidence: 99%

Deep Projective 3D Semantic Segmentation

Lawin¹,

Danelljan²,

Tosteberg³

et al. 2017

Preprint

View full text Add to dashboard Cite

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so far. Recent attempts, based on 3D deep learning approaches (3D-CNNs), have achieved below-expected results. Such methods require voxelizations of the underlying point cloud data, leading to decreased spatial resolution and increased memory consumption. Additionally, 3D-CNNs greatly suffer from the limited availability of annotated datasets. In this paper, we propose an alternative framework that avoids the limitations of 3D-CNNs. Instead of directly solving the problem in 3D, we first project the point cloud onto a set of synthetic 2D-images. These images are then used as input to a 2D-CNN, designed for semantic segmentation. Finally, the obtained prediction scores are re-projected to the point cloud to obtain the segmentation results. We further investigate the impact of multiple modalities, such as color, depth and surface normals, in a multi-stream network architecture. Experiments are performed on the recent Semantic3D dataset. Our approach sets a new stateof-the-art by achieving a relative gain of 7.9%, compared to the previous best approach.

show abstract

“…For the projection needed in our evaluation, we use our own, state-of-the-art projection algorithm, described in [15]. It consists of a flexible framework integrating a multitude of different methods, both state-of-the-art methods as well as own contributions, which were mainly introduced to counter artifacts we discovered during this work.…”

Section: View Projectionmentioning

confidence: 99%

“…Here, we present the PSNR values of the compressed depth-maps, as well as PSNR and Multi-Scale SSIM [16] results of projections using the compressed depth-maps, compared to projections using the ground-truth values. We use our own, state-of-the-art projection algorithm [15] for that. For our evaluation, we use the depth extension of the Sintel datasets [19] (see also figure 1), which provide ground-truth for RGB, depth and camera poses.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

What Is the Best Depth-Map Compression for Depth Image Based Rendering?

Ogniewski

Forssén

2017

Computer Analysis of Images and Patterns

Self Cite

View full text Add to dashboard Cite

Many of the latest smart phones and tablets come with integrated depth sensors, that make depth-maps freely available, thus enabling new forms of applications like rendering from different view points. However, efficient compression exploiting the characteristics of depth-maps as well as the requirements of these new applications is still an open issue. In this paper, we evaluate different depth-map compression algorithms, with a focus on tree-based methods and view projection as application. The contributions of this paper are the following: 1. extensions of existing geometric compression trees, 2. a comparison of a number of different trees, 3. a comparison of them to a state-of-the-art video coder, 4. an evaluation using ground-truth data that considers both depth-maps and predicted frames with arbitrary camera translation and rotation. Despite our best efforts, and contrary to earlier results, current video depth-map compression outperforms tree-based methods in most cases. The reason for this is likely that previous evaluations focused on low-quality, low-resolution depth maps, while high-resolution depth (as needed in the DIBR setting) has been ignored up until now. We also demonstrate that PSNR on depth-maps is not always a good measure of their utility.

show abstract

Pushing the Limits for View Prediction in Video Coding

Cited by 4 publications

References 17 publications

Learning Representations for Segmentation and Registration

Learning Representations for Segmentation and Registration

Deep Projective 3D Semantic Segmentation

What Is the Best Depth-Map Compression for Depth Image Based Rendering?

Contact Info

Product

Resources

About