Ping-Man Lam

Parallelization of cellular neural networks on GPU

Recently, cellular neural networks (CNNs) have been demonstrated to be a highly effective paradigm applicable in a wide range of areas. Typically, CNNs can be implemented using VLSI circuits, but this would unavoidably require additional hardware. On the other hand, we can also implement CNNs purely by software; this, however, would result in very low performance when given a large CNN problem size. Nowadays, conventional desktop computers are usually equipped with programmable graphics processing units (GPUs) that can support parallel data processing. This paper introduces a GPU-based CNN simulator. In detail, we carefully organize the CNN data as 4-channel textures, and efficiently implement the CNN computation as fragment programs running in parallel on a GPU. In this way, we can create a high performance but low-cost CNN simulator. Experimentally, we demonstrate that the resultant GPU-based CNN simulator can run 8-17 times faster than a CPU-based CNN simulator.

An RBF-based compression method for image-based relighting

In image-based relighting, a pixel is associated with a number of sampled radiance values. This paper presents a two-level compression method. In the first level, the plenoptic property of a pixel is approximated by a spherical radial basis function (SRBF) network. That means that the spherical plenoptic function of each pixel is represented by a number of SRBF weights. In the second level, we apply a wavelet-based method to compress these SRBF weights. To reduce the visual artifact due to quantization noise, we develop a constrained method for estimating the SRBF weights. Our proposed approach is superior to JPEG, JPEG2000, and MPEG. Compared with the spherical harmonics approach, our approach has a lower complexity, while the visual quality is comparable. The real-time rendering method for our SRBF representation is also discussed.

Noise-resistant fitting for spherical harmonics

Spherical harmonic (SH) basis functions have been widely used for representing spherical functions in modeling various illumination properties. They can compactly represent low-frequency spherical functions. However, when the unconstrained least square method is used for estimating the SH coefficients of a hemispherical function, the magnitude of these SH coefficients could be very large. Hence, the rendering result is very sensitive to quantization noise (introduced by modern texture compression like S3TC, IEEE half float data type on GPU, or other lossy compression methods) in these SH coefficients. Our experiments show that, as the precision of SH coefficients are reduced, the rendered images may exhibit annoying visual artifacts. To reduce the noise sensitivity of the SH coefficients, this paper first discusses how the magnitude of SH coefficients affects the rendering result when there is quantization noise. Then, two fast fitting methods for estimating the noise-resistant SH coefficients are proposed. They can effectively control the magnitude of the estimated SH coefficients and, hence, suppress the rendering artifacts. Both statistical and visual results confirm our theory.

Self-organizing map-based color palette for high-dynamic range texture compression

High-dynamic range (HDR) images are commonly used in computer graphics for accurate rendering. However, it is inefficient to store these images because of their large data size. Although vector quantization approach can be used to compress them, a large number of representative colors are still needed to preserve acceptable image quality. This paper presents an efficient color quantization approach to compress HDR images. In the proposed approach, a 1D/2D neighborhood structure is defined for the self-organizing map (SOM) approach and the SOM approach is then used to train a color palette. Afterward, a virtual color palette that has more codevectors is simulated by interpolating the trained color palette. The interpolation process is hardware supported in the current graphics hardware. Hence, there is no need to store the virtual color palette as the representative colors are constructed on the fly. Experimental results show that our approach can obtain good image quality with a moderate color palette.

A GPU implementation for LBG and SOM training

Vector quantization (VQ) is an effective technique applicable in a wide range of areas, such as image compression and pattern recognition. The most time-consuming procedure of VQ is codebook training, and two of the frequently used training algorithms are LBG and self-organizing map (SOM). Nowadays, desktop computers are usually equipped with programmable graphics processing units (GPUs), whose parallel data-processing ability is ideal for codebook training acceleration. Although there are some GPU algorithms for LBG training, their implementations suffer from a large amount of data transfer between CPU and GPU and a large number of rendering passes within a training iteration. This paper presents a novel GPU-based training implementation for LBG and SOM training. More specifically, we utilize the random write ability of vertex shader to reduce the overheads mentioned above. Our experimental results show that our approach can run four times faster than the previous approach.

A compression method for a massive image data set in image-based rendering ☆

In image-based rendering with adjustable illumination, the data set contains a large number of pre-captured images under different sampling lighting directions. Instead of individually compressing each pre-captured image, we propose a two-level compression method. Firstly, we use a few spherical harmonic (SH) coefficients to represent the plenoptic property of each pixel. The classical discrete summation method for extracting SH coefficient requires that the sampling lighting directions should be uniformly distributed on the whole spherical surface. It cannot handle the case that the sampling lighting directions are irregularly distributed. A constrained least-squares algorithm is proposed to handle this case. Afterwards, embedded zero-tree wavelet coding is used for removing the spatial redundancy in SH coefficients. Simulation results show our approach is much superior to the JPEG, JPEG2000, MPEG2, and 4D wavelet compression method. The way to allow users to interactively control the lighting condition of a scene is also discussed.

Unicube for Dynamic Environment Mapping

Cube mapping is widely used in many graphics applications due to the availability of hardware support. However, it does not sample the spherical surface evenly. Recently, a uniform spherical mapping, isocube mapping, was proposed. It exploits the six-face structure used in cube mapping and samples the spherical surface evenly. Unfortunately, some texels in isocube mapping are not rectilinear. This nonrectilinear property may degrade the filtering quality. This paper proposes a novel spherical mapping, namely unicube mapping. It has the advantages of cube mapping (exploitation of hardware and rectilinear structure) and isocube mapping (evenly sampling pattern). In the implementation, unicube mapping uses a simple function to modify the lookup vector before the conventional cube map lookup process. Hence, unicube mapping fully exploits the cube map hardware for real-time filtering and lookup. More importantly, its rectilinear partition structure allows a direct and real-time acquisition of the texture environment. This property facilitates dynamic environment mapping in a real time manner.

All-Frequency Lighting with Multiscale Spherical Radial Basis Functions

This paper proposes a novel multiscale spherical radial basis function (MSRBF) representation for all-frequency lighting. It supports the illumination of distant environment as well as the local illumination commonly used in practical applications, such as games. The key is to define a multiscale and hierarchical structure of spherical radial basis functions (SRBFs) with basis functions uniformly distributed over the sphere. The basis functions are divided into multiple levels according to their coverage (widths). Within the same level, SRBFs have the same width. Larger width SRBFs are responsible for lower frequency lighting while the smaller width ones are responsible for the higher frequency lighting. Hence, our approach can achieve the true all-frequency lighting that is not achievable by the single-scale SRBF approach. Besides, the MSRBF approach is scalable as coarser rendering quality can be achieved without reestimating the coefficients from the raw data. With the homogeneous form of basis functions, the rendering is highly efficient. The practicability of the proposed method is demonstrated with real-time rendering and effective compression for tractable storage.

GPU-friendly rendering for illumination adjustable images

An illumination adjustable image (IAI) contains a large number of pre-recorded reference images under various lighting directions. It describes the appearance of a scene illuminated under various lighting directions. Synthesized images about the scene illuminated by complicated lighting conditions are generated from those reference images. This paper presents practical and real-time rendering methods for IAIs based on spherical Gaussian kernel functions (SGKFs). The lighting property of an IAI is represented by a few number of lightmaps. With those lightmaps, we can use consumer-level graphics processing units (GPUs) to perform the rendering process. The rendering methods for directional light source, point light source and slide projector are discussed. Compared with the conventional spherical harmonic (SH) approach, the proposed SGKF approach offers similar distortion performance but it consumes less graphics memory and has a faster rendering speed.

Efficient Relighting of RBF-Based Illumination Adjustable Images

An illumination adjustable image (IAI) contains a large number of prerecorded images under various light directions. Relighting a scene under complicated lighting conditions can be achieved from the IAI. Using the radial basis function (RBF) approach to represent an IAI is proven to be more efficient than using the spherical harmonic approach. However, to represent high-frequency lighting effects, we need to use many RBFs. Hence, the relighting speed could be very slow. This brief investigates a partial reconstruction scheme for relighting an IAI based on the locality of RBFs. Compared with the conventional RBF and spherical harmonics (SH) approaches, the proposed scheme has a much faster relighting speed under the similar distortion performance.