Superpixel alpha-expansion and normal adjustment for stereo matching

Ji, Penglei; Li, Jie; Li, Hanchao; Liu, Xinguo

doi:10.1016/j.jvcir.2021.103238

Cited by 11 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most widely known methods are based on optimization using Markov Random Fields (MRF) [17] and often provide very high-quality estimated depth maps, which is shown in the rankings of the Middlebury database and benchmark [68]. Few of the most accurate methods utilize MRF with segments / patch matching, e.g., [69]- [71]. Such high quality and versatility come at the cost of greater computational complexity than in the case of some deep learning methods.…”

Section: B Depth Estimation For Immersive Videomentioning

confidence: 99%

Overview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video

Mieloch¹,

Garus

Milovanović

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

This paper presents the overview and rationale behind the Decoder-Side Depth Estimation (DSDE) mode of the MPEG Immersive Video (MIV) standard, using the Geometry Absent profile, for efficient compression of immersive multiview video. A MIV bitstream generated by an encoder operating in the DSDE mode does not include depth maps. It only contains the information required to reconstruct them in the client or in the cloud: decoded views and metadata. The paper explains the technical details and techniques supported by this novel MIV DSDE mode. The description additionally includes the specification on Geometry Assistance Supplemental Enhancement Information which helps to reduce the complexity of depth estimation, when performed in the cloud or at the decoder side. The depth estimation in MIV is a non-normative part of the decoding process, therefore, any method can be used to compute the depth maps. This paper lists a set of requirements for depth estimation, induced by the specific characteristics of the DSDE. The depth estimation reference software, continuously and collaboratively developed with MIV to meet these requirements, is presented in this paper. Several original experimental results are presented. The efficiency of the DSDE is compared to two MIV profiles. The combined non-transmission of depth maps and efficient coding of textures enabled by the DSDE leads to efficient compression and rendering quality improvement compared to the usual encoder-side depth estimation. Moreover, results of the first evaluation of state-of-the-art multiview depth estimators in the DSDE context, including machine learning techniques, are presented.

show abstract

Section: B Depth Estimation For Immersive Videomentioning

confidence: 99%

Overview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video

Mieloch¹,

Garus

Milovanović

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Ideally, the estimation of the photo‐consistency must be confined within a certain region, for example, within the boundaries of the target object. Low‐level geometrical features, such as line contours (Bobick & Intille, 1999; Wu et al, 2012), planar segments (Stathopoulou et al, 2023) or superpixels (Ji et al, 2021), are typically used to adaptively select the supporting domain. However, low‐level features are vulnerable to noise and may not correspond to the object boundaries.…”

Section: Introductionmentioning

confidence: 99%

Adaptive region aggregation for multi‐view stereo matching using deformable convolutional networks

Hu,

Su,

Mao

et al. 2023

The Photogrammetric Record

View full text Add to dashboard Cite

Deep‐learning methods have demonstrated promising performance in multi‐view stereo (MVS) applications. However, it remains challenging to apply a geometrical prior on the adaptive matching windows to achieve efficient three‐dimensional reconstruction. To address this problem, this paper proposes a learnable adaptive region aggregation method based on deformable convolutional networks (DCNs), which is integrated into the feature extraction workflow for MVSNet method that uses coarse‐to‐fine structure. Following the conventional pipeline of MVSNet, a DCN is used to densely estimate and apply transformations in our feature extractor, which is composed of a deformable feature pyramid network (DFPN). Furthermore, we introduce a dedicated offset regulariser to promote the convergence of the learnable offsets of the DCN. The effectiveness of the proposed DFPN is validated through quantitative and qualitative evaluations on the BlendedMVS and Tanks and Temples benchmark datasets within a cross‐dataset evaluation setting.

show abstract

“…However, these restrictions do not apply on the energy based methods, variational approaches. It is observed from the literature that many methods have been proposed and implemented to estimate the displacement field that describes the correspondence between the pixels in two images [2,13,14,18,22,24,27].…”

Section: Introductionmentioning

confidence: 99%

Average Error Based Adaptive Regularization Control For The Gradient Constancy Variational Stereo Model

Amur,

Arain

et al. 2023

VFAST trans. math.

View full text Add to dashboard Cite

The study of the stereo vision problems is most crucial and challenging task in image processing and computer vision. The Stereo Vision problems address the investigation of the correspondence between the two images of same scene (stereo pairs) captured from two different views. Generally, these problems are inverse and ill posed. To deal with such problems the energy-based regularization techniques are considered as an efficient and most successful approaches. The adaptive finite element method is used here as discretization method for the partial differential equation obtained from the optimization of the designed energy functional. Such type of the regularization generally depends on the smoothness parameters, and their suitable choice. The choice of the smoothing parameter in an adaptive way and specifically their choice as a scalar function over the whole computational domain is an interesting idea. In this work, a variational model based on the gradient constancy assumption is proposed, moreover a post optimization method (mesh refinement strategy) is designed which is based on a priori estimate called average absolute disparity error estimate. The post optimization is based on an adaptive intelligent algorithm which is efficient in identifying the less regular regions of the computed disparity image and reduces the value of the parameter to refine the grid. Consequently, the smoothness appears in the solution which is the main goal.

show abstract

Superpixel alpha-expansion and normal adjustment for stereo matching

Cited by 11 publications

References 17 publications

Overview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video

Overview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video

Adaptive region aggregation for multi‐view stereo matching using deformable convolutional networks

Average Error Based Adaptive Regularization Control For The Gradient Constancy Variational Stereo Model

Contact Info

Product

Resources

About