Georgios Georgiadis, Alessandro Chiuso, Stefano Soatto · 2013
We characterize ``visual textures'' as realizations of a stationary, ergodic, Markovian process, and propose using its approximate minimal sufficient statistics for compressing texture images. We propose inference algorithms for estimating the ``state'' of such process and its ``variability''. These represent the encoding stage. We also propose a non-parametric sampling scheme for decoding, by synthesizing textures from their encoding. While these are not faithful reproductions of the original textures (so they would fail a comparison test based on PSNR), they capture the statistical properties of the underlying process, as we demonstrate empirically. We also quantify the tradeoff between fidelity (measured by a proxy of a perceptual score) and complexity.
Cited by 8
L. Nachtergaele, B. Vanhoof, M. Peón et al. · 2014
Cited by 0
Simon Fenney · 2003
This paper presents a new, lossy texture compression technique that is suited to implementation on low-cost, low-bandwidth devices as well as more powerful rendering systems. It uses a representation that is based on the blending of two (or more) `low frequency' signals using a high frequency but low precision modulation signal. Continuity of
Cited by 0
Andújar Gran, Carlos Antonio, Martínez Bayona, Jonás · RECERCAT (Consorci de Serveis Universitaris de Catalunya)
Current schemes for texture compression fail to exploit spatial coherence in an adaptive manner due to the strict efficiency constraints imposed by GPU-based, fragment-level decompression. In this paper we present a texture compression framework for quasi-lossless, locally-adaptive compression of graphics data. Key elements include a Hilbert scan to maximize spatial coherence, efficient encoding of homogeneous image regions through arbitrarilysized texel runs, a cumulative run-length encoding supporting fast random-access, and a compression algorithm suitable for fixed-rate and variable-rate encoding. Our scheme can be easily integrated into the rasterization\npipeline of current programmable graphics hardware allowing real-time GPU decompression. We show that our scheme clearly outperforms competing approaches such as S3TC DXT1 on a large class of images with some degree of spatial coherence. Unlike other proprietary formats, our scheme is suitable for compression of any graphics data including color maps, shadow maps and relief maps. We have observed compression rates of up to 12:1, with minimal or no loss in visual quality and a small impact on rendering time.
Cited by 0Open access
Nystad, Jorn, Lassen, Anders, Pomianowski, Andy et al. · Eurographics · 2012
We describe a fixed-rate, lossy texture compression system that is designed to offer an unusual degree of flexibility and to support a very wide range of use cases, while providing better image quality than most formats in common use today. The system supports both 2D and 3D textures, at both standard and high dynamic range, at bit rates ranging from eight bits per pixel down to less than one bit per pixel in very fine steps. At any bit rate, texels can have from one to four color components. The system's flexibility results from a number of novel features. Color spaces and weights are represented using an encoding scheme that allows flexible allocation of bits between different types of information. The system uses bilinear interpolation to derive color space coordinates for a texel from sparse samples, and uses a procedural partition function to map texels to color spaces.
Cited by 3Open access
Shin Fujieda, Takahiro Harada · arXiv (Cornell University) · 2024
Block compression is a widely used technique to compress textures in real-time graphics applications, offering a reduction in storage size. However, their storage efficiency is constrained by the fixed compression ratio, which substantially increases storage size when hundreds of high-quality textures are required. In this paper, we propose a novel block texture compression method with neural networks, Neural Texture Block Compression (NTBC). NTBC learns the mapping from uncompressed textures to block-compressed textures, which allows for significantly reduced storage costs without any change in the shaders.Our experiments show that NTBC can achieve reasonable-quality results with up to about 70% less storage footprint, preserving real-time performance with a modest computational overhead at the texture loading phase in the graphics pipeline.
Cited by 1Open access
Kimmo Roimela, Tomi Aarnio, Joonas Itäranta · ACM Transactions on Graphics · 2006
We present a novel compression scheme for high dynamic range textures, targeted for hardware implementation. Our method encodes images at a constant 8 bits per pixel, for a compression ratio of 6:1. We demonstrate that our method achieves good visual fidelity, surpassing DXTC texture compression of RGBE data which is the most practical method on existing graphics hardware. The decoding logic for our method is simple enough to be implemented as part of the texture fetch unit in graphics hardware.
Cited by 32
Pavlos Mavridis, Γεώργιος Παπαϊωάννου · Computer Graphics Forum · 2012
Abstract In this paper we introduce a new fixed‐rate texture compression scheme based on the energy compaction properties of a modified Haar transform. The coefficients of this transform are quantized and stored using standard block compression methods, such as DXTC and BC7, ensuring simple implementation and very fast decoding speeds. Furthermore, coefficients with the highest contribution to the final image are quantized with higher accuracy, improving the overall compression quality. The proposed modifications to the standard Haar transform, along with a number of additional optimizations, improve the coefficient quantization and reduce the compression error. The resulting method offers more flexibility than the currently available texture compression formats, providing a variety of additional low bitrate encoding modes for the compression of grayscale and color textures.
Cited by 7Open access
Byrne, James · OpenGrey (Institut de l'Information Scientifique et Technique) · 2012
Still image compression methods have changed little over the last ten years. Mean- while, the quantity of content transmitted over limited bandwidth channels has increased dramatically. The currently available methods are content agnostic: that I is they use the same compression process independent of the content at any given spatial location. Region specific coding provides one possible route to increased compression performance. Texture regions in particular are usually not conceptually important to a viewer of an image, but the high frequency nature of such regions consumes many bits when encoding. Texture synthesis is the process of generating textures from a sample or parameter set, and thus if these texture regions can be encoded by spec- ifying texture synthesis at the decoder, it may be possible to save large amounts of data, without detriment to the decoded image quality. This thesis presents a number of adaptations to the Graphcut patch based texture synthesis method, to make it suitable for constrained synthesis of texture regions in natural images. This includes a colour matching process to account for luminance and chrominance changes over the texture region, and a modification to allow constrained synthesis of an arbitrarily shaped region. This architecture is then integrated into two complete image compression by synthesis systems based on JPEG and JPEG2000 respectively. In each case the image is segmented, anal- ysed and synthesis occurs at the decoder to fill in removed texture regions. In the system based on JPEG2000 a feedback loop is included which makes some assess- ment of the quality of the synthesis at the encoder in order to adapt the synthesis parameters to improve the result quality, or to skip synthesis entirely if deemed necessary. The results of these systems show some promise in that substantial savings can be made over transform coded images coded at the same Q value as the residual image. However it is observed that synthesis can be detrimental to the quality of the image in comparison to an equivalent traditionally coded image at the same bitrate. Two methods of texture orientation analysis for non-homogeneous textures are presented. One of these in particular produces a good assessment of the texture orientation. This method uses a Steerable Pyramid transform to analyse the orientations. Then, two methods of sample selection and synthesis using the analysed texture orientation are presented. These methods aim to recreate the original texture's orientation variation from a smaller texture sample and the orientation map. The best of these methods selects one or more samples containing multiple orientations and selects texture patches appropriately oriented to the current location of synthesis.
Cited by 0
Using Interpolative Vector, Young-su Kwon, In-cheol Park et al. · 2000
Texture mapping is a common technique used to increase the visual quality of 3D scenes. As texture mapping requires large memory to deal with large textures generally required in the current visual systems, we propose an algorithm for compressing a pyramid texture used for mipmapping. Vector quantization is used to compress all levels of the pyramid texture to one representative value databook, one residual codebook and one index map. The proposed compression scheme uses interpolative texel difference vector quantization that compresses the difference between the interpolated surfaces generated by the representative value and the correct uncompressed texels of the texture at each level. The compressed pyramid texture can be accessed randomly and decompressed without loss of visual quality. We also propose a hardware architecture that performs the trillnear filtering with the compressed pyramid texture.
Cited by 0
Siegfried Matthies, Galina W. Vinel, Kurt Helming · 1987
Cited by 0
Антон Валерьевич Переберин · 2007
We introduce a hierarchical approach for hardware-aided texture compression. The hierarchical representation is combined with a block-wise approach that is used in some existing texture compression techniques. Our method is an attempt to merge texture compression and mip-mapping.
Cited by 27
C. Bregler, M. Wimmer, Pavlos Mavridis et al. · 2016
5 bpp 3 bpp 2.25 bpp 1.75 bpp 2 bpp Figure 1: Our method encodes grayscale and color images at various bitrates, improving the flexibility of existing texture compression formats. In this paper we introduce a new fixed-rate texture compression scheme based on the energy compaction properties of a modified Haar transform. The coefficients of this transform are quantized and stored using standard block compression methods, such as DXTC and BC7, ensuring simple implementation and very fast decoding speeds. Furthermore, coefficients with the highest contribution to the final image are quantized with higher accuracy, improving the overall compression quality. The proposed modifications to the standard Haar transform, along with a number of additional optimizations, improve the coefficient quantization and reduce the compression error. The resulting method offers more flexibility than the currently available texture compression formats, providing a variety of additional low bitrate encoding modes for the compression of grayscale and color textures.
Cited by 0
Vinayak K. Bairagi, A. M. Sapkal, Ankita Tapaswi · Journal of Digital Imaging · 2012
Image processing is one of the most researched areas these days due to the flooding of the internet with an overload of images. The noble medicine industry is not left untouched. It has also suffered with an excess of patient record storage and maintenance. With the advent of automation of the industries in the world, the medicine industry has sought to change and provide a more portable feel to it, leading to the fields of telemedicine and such. Our algorithm comes in handy in such scenarios where large amount of data needs to be transmitted over the network for perusal by another consultant. We aim for a visual quality approach in our algorithm rather than pixel-wise fidelity. We utilize parameters of edges and textures as the basic parameters in our compression algorithm.
Cited by 12Open access
Jacob Ström, Tomas Akenine-Möller · 2004
Introduction We present a new lossy texture compression (TC) scheme, targeted for mobile devices, which compresses 2 4 pixel blocks into 32 bits. Compared to our POOMA TC work [Akenine-M oller and Str om 2003], peak signal to noise ratio (PSNR) is improved by 0.6 dB on average, the bit rate is reduced from 5.33 bits per pixel (bpp) to 4 bpp, and we avoid 23 blocks that are awkward for hardware implementation. Most mobile devices, such as phones and PDAs, have very limited available memory bandwidth, e.g., 16 or 32 bits/cycle. For 3D graphics applications, TC is therefore a fundamental technique for reducing bandwidth usage. Most TC schemes compress each block of pixels individually. In general it is simpler to compress larger blocks efficiently, and therefore the most common block size is 4 4 pixels compressed into 64 bits (S3TC, DXTC). If a compressed block occupies the same number of bits as the bus width (e.g., 32 bits), then pipeline stalls can be avoided [AkenineM oller and S
Cited by 0
Shruti Bansal, Santanu Chaudhury, Brejesh Lall · 2013
In this paper, a dynamic texture based compression scheme is devised for videos. Correspondence analysis is explored for the analysis of motion patterns in a video on the basis of optic flow data and then clusters of different motion patterns are created. Dynamic textures tend to disobey Horn and Schunck's assumption of brightness constancy and hence, optic flow residual is used as an indicator of their presence. The correspondence analysis results and optic flow residual are combined together in a new segmentation scheme. The optic flow data tracks the motion of groups of pixels to generate the flow lines. These flow lines are used in a synthesis scheme for creating an illusion of continuously flowing texture. The integration of this synthesis scheme in the compression format gives us considerable bit stream reduction corresponding to the dynamic texture regions. The scheme is integrated with standard H.264/AVC model, texture regions that do not fall under the above precinct of dynamic textures and non-texture regions are encoded-decoded by the H.264 model directly.
Cited by 2
Marc Bosch, Fengqing Zhu, Edward J. Delp · Proceedings - International Conference on Image Processing · 2007
In this paper we integrate several spatial texture tools into a texture-based video coding scheme. We implemented texture techniques and segmentation strategies in order to detect texture regions in video sequences. These textures are analyzed using temporal motion techniques and are labeled as skipped areas that are not encoded. After the decoding process, frame reconstruction is performed by inserting the skipped texture areas into the decoded frames. We are able to show an improvement over previous texture-based implementations in terms of compression efficiency.
Cited by 27
Zhuang, Tao, Liu, Wentao, Liu, Ligang · Eurographics · 2025
In real-time rendering, neural network models using neural textures (texture-form neural features) are increasingly applied. For high-memory scenarios like film-grade games, reducing neural texture memory overhead is critical. While neural textures can use hardware-accelerated block compression for memory savings and leverage hardware texture filtering for performance, mainstream block compression encoders only aim to minimize compression errors. This design may significantly increase neural network model loss.We propose a novel differentiable block compression (DBC) framework that integrates encoding and decoding into neural network optimization training. Compared with direct compression by mainstream encoders, end-to-end trained neural textures reduce model loss. The framework first enables differentiable encoding computation, then uses a compressionerror- based stochastic sampling strategy for encoding configuration selection. A Mixture of Partitions (MoP) module is introduced to reduce computational costs from multiple partition configurations. As DBC employs native block compression formats, inference maintains real-time performance.
Cited by 0Open access
Gernot Ziegler Hendrik, Hendrik P. A. Lensch, Naveed Ahmed et al. · 2004
We present a model-based approach to encode multiple synchronized video streams depicting a dynamic scene from different viewpoints. With approximate 3D scene geometry available, we compensate for motion as well as disparity by transforming all video images to object textures prior to compression. A two-level hierarchical coding strategy is employed to efficiently exploit inter-texture coherence as well as to ensure quick random access during decoding. Experimental validation shows that attainable compression ratios range up to 50:1 without subsampling. The proposed coding scheme is intended for use in conjunction with FreeViewpoint Video and 3D-TV applications.
Cited by 0
S. de Waele, Fei Zuo · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2007
Low-bitrate digital video often suffers from the artifact of texture flattening. Texture synthesis can be used to revive the removed texture. Patch-based synthesis provides a quite general method for texture synthesis. However, this method still requires a substantial bitrate to transmit example patches. We propose a method for stochastic texture synthesis which requires only a very low bitrate (less than 1 kbit/sec) that can replace patch-based synthesis for random textures. Spatial correlation is modeled as a 2-dimensional Moving Average (MA) process. To achieve a faithful representation of temporal evolution, we use a translation+scaling motion model combined with a finite impulse response (FIR) filter. Experiments show that we can successfully reduce texture flattening for a range of random textures such as grass and roads.
Cited by 2