Error Resilient and Energy Efficient MRF Message-Passing-Based Stereo Matching

This paper presents a low-power digital filtering technique derived via algorithmic noise-tolerance (ANT). The proposed technique achieves substantial energy savings via voltage overscaling (VOS), where the supply voltage is scaled beyond the minimum (referred to as V/sub dd-crit/) necessary for correct operation. The resulting performance degradation is compensated for via an adaptive error-cancellation (AEC) algorithm. In particular, we employ an energy optimum AEC to optimize the energy-performance trade-off and reduce the overhead due to ANT. It is shown that the proposed AEC technique is well-suited for designing low-power broadband signal processing and communication systems. Up to 71% energy savings over optimally voltage-scaled conventional systems can be obtained in the context of frequency-division multiplexed (FDM) communications without incurring any performance loss.

Approximate computing is established as a design alternative to improve the energy requirements of a vast number of applications, leveraging their intrinsic error tolerance. Voltage over-scaling (VOS) is one of the most energy-efficient approximation techniques, but its exploitation is still limited due to the large errors it induces. In this work, we investigate, for the first time, the resiliency of negative capacitance transistor (NCFET) technology to VOS in comparison to conventional CMOS technology. Our work reveals that circuits implemented using the NCFET technology exhibit much less timing errors under VOS due to the inherent voltage amplification provided by the ferroelectric layer. NCFET is one of the very promising emerging technologies that is rapidly evolving for low-power circuit as it enables the transistors to switch faster without the need to increase the voltage. We demonstrate how NCFET technology allows circuit designers to effectively employ VOS to boost the efficiency of their approximate circuits, while still keeping the induced errors marginal. Our analysis shows that the VOS-resilience of NCFET circuits enables maximizing the voltage decrease and thus, NCFET based VOS approximate circuits achieve from 1.83× up to 2.78× higher energy reduction compared to the corresponding FinFET circuits for the same error bounds.

Stereo matching is the process of finding disparity map between a pair of stereo images. Markov Random Field (MRF) model has been used in stereo matching algorithms in which the goal is to minimize total data, smoothness and occlusion cost. Recent MRF based stereo matching algorithms assign the same smoothness cost to adjacent pixels which is not effective at objects boundaries. In this paper, we propose a method to constrain the smoothness cost such that the cost applied to disparity discontinuity within an object is higher than that of the object's boundary. Data cost function is also normalized before computing its probability distribution function (PDF) to enforce an uniform PDF for the entire image. Experimental results have demonstrated that the proposed method is competitive to the state-of-the-art stereo matching algorithms.

Manufacturing and environmental variability lead to timing errors in computing systems that are typically corrected by error detection and correction mechanisms at the circuit level. The cost and speed of recovery can be improved by memoization-based optimization methods that exploit spatial or temporal parallelisms in suitable computing fabrics such as general-purpose graphics processing units (GPGPUs). We propose here a temporal memoization technique for use in floating-point units (FPUs) in GPGPUs that uses value locality inside data-parallel programs. The technique recalls (memorizes) the context of error-free execution of an instruction on a FPU. To enable scalable and independent recovery, a single-cycle lookup table (LUT) is tightly coupled to every FPU to maintain contexts of recent error-free executions. The LUT reuses these memorized contexts to exactly, or approximately, correct errant FP instructions based on application needs. In real-world applications, the temporal memoization technique achieves an average energy saving of 8%-28% for a wide range of timing error rates (0%-4%) and outperforms recent advances in resilient architectures. This technique also enhances robustness in the voltage overscaling regime and achieves relative average energy saving of 66 % with 11% voltage overscaling.

Recent research shows that estimating labels and graph structures simultaneously in Markov random Fields can be achieved via solving LP problems. The scalability is a bottleneck that prevents applying such technique to larger problems such as image segmentation and object detection. Here we present a fast message passing algorithm based on the mixed-integer bilinear programming formulation of the original problem. We apply our algorithm to both synthetic data and real-world applications. It compares favourably with previous methods.KeywordsMessage-passing AlgorithmUnknown GraphMixed Integer Bilinear ProgrammingSuperpixelsSemantic Image SegmentationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A new framework is presented for both understanding and developing graph-cut-based combinatorial algorithms suitable for the approximate optimization of a very wide class of Markov Random Fields (MRFs) that are frequently encountered in computer vision. The proposed framework utilizes tools from the duality theory of linear programming in order to provide an alternative and more general view of state-of-the-art techniques like the \alpha-expansion algorithm, which is included merely as a special case. Moreover, contrary to \alpha-expansion, the derived algorithms generate solutions with guaranteed optimality properties for a much wider class of problems, for example, even for MRFs with nonmetric potentials. In addition, they are capable of providing per-instance suboptimality bounds in all occasions, including discrete MRFs with an arbitrary potential function. These bounds prove to be very tight in practice (that is, very close to 1), which means that the resulting solutions are almost optimal. Our algorithms' effectiveness is demonstrated by presenting experimental results on a variety of low-level vision tasks, such as stereo matching, image restoration, image completion, and optical flow estimation, as well as on synthetic problems.

Many vision applications have been formulated as Markov Random Field (MRF) problems. Although many of them are discrete labeling problems, continuous formulation often achieves great improvement on the qualities of the solutions in some applications such as stereo matching and optical flow. In continuous formulation, however, it is much more difficult to optimize the target functions. In this paper, we propose a new method called fusion move driven Markov Chain Monte Carlo method (MCMC-F) that combines the Markov Chain Monte Carlo method and the fusion move to solve continuous MRF problems effectively. This algorithm exploits powerful fusion move while it fully explore the whole solution space. We evaluate it using the stereo matching problem. We empirically demonstrate that the proposed algorithm is more stable and always finds lower energy states than the state-of-the art optimization techniques.

This paper proposes a stochastic approach to estimate the occlusion and disparity fields of stereoscopic images. The fields are estimated by the Bayesian maximum a posteriori (MAP) framework and Markov random field (MRF) models. The occlusion field model is based on the stochastic observation that the probability distribution in MAP estimator is relatively unstable and uniform at occluded regions. The occlusion is explicitly modelled as MRF, and is estimated in an energy optimization method called stochastic diffusion. The detected occluded region is compensated for the re-estimated disparity field in the same stochastic diffusion and the dynamic programming approach. Experimental results show good occlusion detection and disparity estimation. These results show the novel stochastic approach is suitable for occlusion detection and disparity estimation.

In this paper, we propose a multi-scale Bayesian networks model and its inference algorithm. We use the multi-scale Bayesian networks model to segment the Synthetic Aperture Radar (SAR) image. The multi-scale Bayesian networks is constructed accordance with the multi-scale sequence of SAR images, whose MAP value is performed using the Belief Propagation (BP) algorithm and the corresponding parameter estimation is finished by the Expectation-Maximization (EM) algorithm. Experimental results demonstrate that the proposed multi-scale Bayesian networks model outperform the single-scale Bayesian network model and Markov Random Field - Intersecting Cortical Model (MRF-ICM).

Fitting multiple projective models using clustering-based Markov chain Monte Carlo inference

Interactive Image Segmentation has attracted much attention in the vision and graphics community recently. A typical application for interactive image segmentation is foreground/background segmentation based on user specified brush labellings. The problem can be formulated within the binary Markov Random Field (MRF) framework which can be solved efficiently via graph cut [1]. However, no attempt has yet been made to handle segmentation of multiple regions using graph cuts. In this paper, we propose a multiclass interactive image segmentation algorithm based on the Potts MRF model. Following [2], this can be converted to a multiway cut problem first proposed in [2] and solved by expansion-move algorithms for approximate inference [2]. A faster algorithm is proposed in this paper for efficient solution of the multiway cut problem based on partial optimal labeling. To achieve this, we combine the one-vs-all classifier fusion framework with the expansion-move algorithm for label inference over large images. We justify our approach with both theoretical analysis and experimental validation.

In this paper, we propose a disparity refinement method that directly refines the winner-take-all (WTA) disparity map by exploring its statistical significance. According to the primary steps of the segment-based stereo matching, the reference image is over-segmented into superpixels and a disparity plane is fitted for each superpixel by an improved random sample consensus (RANSAC). We design a two-layer optimization to refine the disparity plane. In the global optimization, mean disparities of superpixels are estimated by Markov random field (MRF) inference, and then, a 3D neighborhood system is derived from the mean disparities for occlusion handling. In the local optimization, a probability model exploiting Bayesian inference and Bayesian prediction is adopted and achieves second-order smoothness implicitly among 3D neighbors. The two-layer optimization is a pure disparity refinement method because no correlation information between stereo image pairs is demanded during the refinement. Experimental results on the Middlebury and KITTI datasets demonstrate that the proposed method can perform accurate stereo matching with a faster speed and handle the occlusion effectively. It can be indicated that the "matching cost computation + disparity refinement" framework is a possible solution to produce accurate disparity map at low computational cost.

Recent work on early vision such as image segmentation, image restoration, stereo matching, and optical flow models these problems using Markov Random Fields. Although this formulation yields an NP-hard energy minimization problem, good heuristics have been developed based on graph cuts and belief propagation. Nevertheless both approaches still require tens of seconds to solve stereo problems on recent PCs. Such running times are impractical for optical flow and many image segmentation and restoration problems. We show how to reduce the computational complexity of belief propagation by applying the Four Color Theorem to limit the maximum number of labels in the underlying image segmentation to at most four. We show that this provides substantial speed improvements for large inputs to a variety of vision problems, while maintaining competitive result quality.KeywordsImage SegmentationBelief PropagationMarkov Random FieldsImage RestorationStereo MatchThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The maximum a posteriori assignment for general structure Markov random fields is computationally intractable. In this paper, we exploit tree-based methods to efficiently address this problem. Our novel method, named Tree-based Iterated Local Search (T-ILS), takes advantage of the tractability of tree-structures embedded within MRFs to derive strong local search in an ILS framework. The method efficiently explores exponentially large neighborhoods using a limited memory without any requirement on the cost functions. We evaluate the T-ILS on a simulated Ising model and two real-world vision problems: stereo matching and image denoising. Experimental results demonstrate that our methods are competitive against state-of-the-art rivals with significant computational gain.

Light-field stereo matching problems are commonly modeled by Markov Random Fields (MRFs) for statistical inference of depth maps. Nevertheless, most previous approaches did not adapt to image statistics but instead adopted fixed model parameters. They explored explicit vision cues, such as depth consistency and occlusion, to provide local adaptability and enhance depth quality. However, such additional assumptions could end up confining their applicability, e.g. algorithms designed for dense view sampling are not suitable for sparse one. In this paper, we get back to MRF fundamentals and develop an empirical Bayesian framework-Robust Pseudo Random Field-to explore intrinsic statistical cues for broad applicability. Based on pseudo-likelihoods with hidden soft-decision priors, we apply soft expectation-maximization (EM) for good model fitting and perform hard EM for robust depth estimation. We introduce novel pixel difference models to enable such adaptability and robustness simultaneously. Accordingly, we devise a stereo matching algorithm to employ this framework on dense, sparse, and even denoised light fields. It can be applied to both true-color and grey-scale pixels. Experimental results show that it estimates scene-dependent parameters robustly and converges quickly. In terms of depth accuracy and computation speed, it also outperforms state-of-the-art algorithms constantly.