Learning Graph Regularisation for Guided Super-Resolution

Lutio, Riccardo de; Becker, Alexander; D’Aronco, Stefano; Russo, Stefania; Wegner, Jan Dirk; Schindler, Konrad

doi:10.1109/cvpr52688.2022.00202

Cited by 29 publications

(18 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GraphSR [17] CVPR-2022 Proposes to learn the affinity graph and then embeds the learned graph to a differentiable optimisation layer to regularize the upsampling process.…”

Section: Total Variationmentioning

confidence: 99%

“…Recent advances of deep learning algorithms have revolutionized the area of computer vision; tremendous progress has been achieved in a variety of domains, such as image classification [27,46], object localization [131,147] and semantic segmentation [108,151]. GDSR is no exception: a myriad of neural networks have been developed and advanced the state of the art [17,154,156]. The learning-based method is suitable for a scene where there is a large amount of training data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Guided Depth Map Super-resolution: A Survey

Zhang¹,

Liu²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution (HR) depth map from a low-resolution (LR) observation with the help of a paired HR color image, is a longstanding and fundamental problem, it has attracted considerable attention from computer vision and image processing communities. A myriad of novel and effective approaches have been proposed recently, especially with powerful deep learning techniques. This survey is an effort to present a comprehensive survey of recent progress in GDSR. We start by summarizing the problem of GDSR and explaining why it is challenging. Next, we introduce some commonly used datasets and image quality assessment methods. In addition, we roughly classify existing GDSR methods into three categories, i.e., filtering-based methods, prior-based methods, and learning-based methods. In each category, we introduce the general description of the published algorithms and design principles, summarize the representative methods, and discuss their highlights and limitations. Moreover, the depth related applications are introduced. Furthermore, we conduct experiments to evaluate the performance of some representative methods based on unified experimental configurations, so as to offer a systematic and fair performance evaluation to readers. Finally, we conclude this survey with possible directions and open problems for further research. All the related materials can be found at https://github.com/zhwzhong/Guided-Depth-Map-Super-resolution-A-Survey.CCS Concepts: • General and reference → Surveys and overviews.

show abstract

“…GraphSR [17] CVPR-2022 Proposes to learn the affinity graph and then embeds the learned graph to a differentiable optimisation layer to regularize the upsampling process.…”

Section: Total Variationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Guided Depth Map Super-resolution: A Survey

Zhang¹,

Liu²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Depth enhancement algorithms convert a degraded depth map into a high-quality one, usually with guidance from a high-quality RGB image [23]. They can be roughly divided into two categories: depth completion [24,33,41,46,53] and depth super-resolution [16,32,48]. Depth completion algorithms assume a high-resolution depth map with holes or being sparse, and the algorithm inpaints the missing depth by propagating information from the reliable pixels [24,41].…”

Section: Depth Enhancement Algorithmsmentioning

confidence: 99%

“…Lutio et al [32] model the guided super-resolution process as a pixel-to-pixel mapping and learn it at test-time. The authors further propose a graph-based optimization algorithm to improve the performance [16]. However, they assume the low-resolution depth map is generated with a weighted average sampler (i.e., bilinear downsampling), which is inconsistent with physical image formation models.…”

Section: Depth Enhancement Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Consistent Direct Time-of-Flight Video Depth Super-Resolution

Sun¹,

Ye²,

Xiong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Figure 1. We propose the first multi-frame approaches, dToF depth video super-resolution (DVSR) and histogram video super-resolution (HVSR), to super-resolve low-resolution dToF sensor videos with the high-resolution RGB frame guidance. The point cloud visualizations of depth predictions reveal that, by utilizing multi-frame correlation, DVSR predicts significantly better geometry compared to state-of-theart per-frame depth enhancement networks [41] while being more lightweight; HVSR further improves the fidelity of geometry and reduces flying pixels by utilizing the dToF histogram information. Besides the improvements in per-frame estimation, we highly recommend readers to check out the supplementary video, which visualizes the significant improvements in temporal stability across the entire sequences.

show abstract