A depth estimating method from a single image using FoE CRF

Wang, Xiaoyan; Hou, Chunping; Pu, Liangzhou; Hou, Yonghong

doi:10.1007/s11042-014-2130-z

Cited by 14 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, many more probabilistic modeling approaches have been proposed recently, as reported for instance in [30] and [31]. Enlightened by psychophysical evidence of visual processing in human Vision System (HVS) and Natural Scene Statistics (NSS) models of image and range, [30] proposed a Bayesian framework to recover the range information from monocular image by adopting the statistical relationships between luminance and depth in natural scenes.…”

Section: Related Workmentioning

confidence: 99%

“…Enlightened by psychophysical evidence of visual processing in human Vision System (HVS) and Natural Scene Statistics (NSS) models of image and range, [30] proposed a Bayesian framework to recover the range information from monocular image by adopting the statistical relationships between luminance and depth in natural scenes. In [31], Xiaoyan Wang et al proposed a depth estimation conditional random field (CRF) model with the field of experts (FoE) as the prior.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

SuperDepthTransfer: Depth Extraction from Image Using Instance-Based Learning with Superpixels

2017

KSII TIIS

View full text Add to dashboard Cite

In this paper, we primarily address the difficulty of automatic generation of a plausible depth map from a single image in an unstructured environment. The aim is to extrapolate a depth map with a more correct, rich, and distinct depth order, which is both quantitatively accurate as well as visually pleasing. Our technique, which is fundamentally based on a preexisting DepthTransfer algorithm, transfers depth information at the level of superpixels. This occurs within a framework that replaces a pixel basis with one of instance-based learning. A vital superpixels feature enhancing matching precision is posterior incorporation of predictive semantic labels into the depth extraction procedure. Finally, a modified Cross Bilateral Filter is leveraged to augment the final depth field. For training and evaluation, experiments were conducted using the Make3D Range Image Dataset and vividly demonstrate that this depth estimation method outperforms state-of-the-art methods for the correlation coefficient metric, mean log10 error and root mean squared error, and achieves comparable performance for the average relative error metric in both efficacy and computational efficiency. This approach can be utilized to automatically convert 2D images into stereo for 3D visualization, producing anaglyph images that are visually superior in realism and simultaneously more immersive.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

SuperDepthTransfer: Depth Extraction from Image Using Instance-Based Learning with Superpixels

2017

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…In traditional monocular depth estimation, some methods build the energy function from Markov Random Fields (MRFs) or Conditional Random Fields (CRFs) [28,29,35]. They exploit the observation cues, such as the texture and position information, along with the last prediction to build the energy function, and then optimize this energy to obtain a depth prediction.…”

Section: Introductionmentioning

confidence: 99%

NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

Yuan¹,

Gu²,

Dai³

et al. 2022

Preprint

View full text Add to dashboard Cite

Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset. The source code of our method will be made public.

show abstract

“…It is [7] that for the first time claimed that the MMSE estimation can lead to better performance compared with the MAP estimation for the image denoising task with their learned FoE image prior model. After that, many works follow their suggestion to make use of the MMSE estimation for FoE related models, such as image deblurring [12, 13], image denoising [8], depth estimation [14, 15], image separation [9] and single image super resolution (SR) [10].…”

Section: Introductionmentioning

confidence: 99%

“…After that, many works follow their suggestion to make use of the MMSE estimation for FoE related models, such as image deblurring [14], [21], image denoising [4], depth estimation [16], [5], image separation [19] and single image super resolution [20].…”

mentioning

confidence: 99%

Higher‐order MRFs based image super resolution: why not MAP?

Chen

2016

IET Image Processing

View full text Add to dashboard Cite

A trainable filter-based higher-order Markov Random Fields (MRFs) model -the so called Fields of Experts (FoE), has proved a highly effective image prior model for many classic image restoration problems. Generally, two options are available to incorporate the learned FoE prior in the inference procedure:(1) sampling-based minimum mean square error (MMSE) estimate, and (2) energy minimization-based maximum a posteriori (MAP) estimate. This paper is devoted to the FoE prior based single image super resolution (SR) problem, and we suggest to make use of the MAP estimate for inference based on two facts: (I) It is well-known that the MAP inference has a remarkable advantage of high computational efficiency, while the sampling-based MMSE estimate is very time consuming. (II) Practical SR experiment results demonstrate that the MAP estimate works equally well compared to the MMSE estimate with exactly the same FoE prior model. Moreover, it can lead to even further improvements by incorporating our discriminatively trained FoE prior model. In summary, we hold that for higher-order natural image prior based SR problem, it is better to employ the MAP estimate for inference. I. INTRODUCTIONMarkov Random Fields (MRFs) based models have a long history in low-level computer vision problems, which treat the image (can be also seen as a label field) as a random field [7]. It is well-known that MRFs are particularly effective for image/label prior modeling in image processing. In a MRF-based prior model, the probability of a whole field is defined based on the potential (or energy) of the local cliques. MRF-based prior models, especially higher-order potentials for enforcing label consistency have demonstrated great successes in the community of multi-label image segmentation [9], [6]. The exploited Y.J. Chen is with the

show abstract

A depth estimating method from a single image using FoE CRF

Cited by 14 publications

References 15 publications

SuperDepthTransfer: Depth Extraction from Image Using Instance-Based Learning with Superpixels

SuperDepthTransfer: Depth Extraction from Image Using Instance-Based Learning with Superpixels

NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

Higher‐order MRFs based image super resolution: why not MAP?

Contact Info

Product

Resources

About