Hardware for superior texture performance

Knittel, Günter; Schilling, Andreas; Kugler, Anders; Straßer, Wolfgang

doi:10.1016/0097-8493(96)00019-2

Cited by 31 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from the general image compression methods such as JPEG, the texture compression algorithm are optimized for random access. According to [5], the existing texture compression methods can be classified into 3 categories: Vector Quantization (VQ) [6,7], Block based compression [8][9][10][11][12][13] and High Dynamic Range (HDR) texture compression [14 -17].…”

Section: B Texture Simplificationmentioning

confidence: 99%

A multiple representation data structure of 3D building textures

Mao

Ban

2011

2011 19th International Conference on Geoinformatics

View full text Add to dashboard Cite

Texture is an important element for visualization of 3D city models and often takes a big proportion of the total data volume. In order to simplify 3D city model textures for dynamic visualization in different scales, a multiple representation data structure, TextureTree is proposed to store building textures in different LoDs. First, the texture image is iteratively segmented by horizontal or vertical dividing zone (edge or background from edge detection) until each sections are basically in the same color. Then textures in all sections are represented by their main color and the TextureTree is created based on the color difference between the adjacent sections. With the TextureTree, the simplified texture in different LoDs can be dynamically generated. The experiment results show that the data volume of building textures can be reduced by TextureTree while the required visual similarity is preserved.

show abstract

Section: B Texture Simplificationmentioning

confidence: 99%

A multiple representation data structure of 3D building textures

Mao

Ban

2011

2011 19th International Conference on Geoinformatics

View full text Add to dashboard Cite

show abstract

“…In LDR rendering, 24 bpp raw RGB textures are rarely used because they consume too much storage and bandwidth. Rendering with compressed LDR textures is preferred and has been proposed to enhance the real-time performance [5], [6], [7]. The bandwidth and storage demands are even greater with HDR rendering, where texture samples commonly use floating-point representations (usually 48 or 96 bpp).…”

Section: Introductionmentioning

confidence: 99%

High-Dynamic-Range Texture Compression for Rendering Systems of Different Capacities

Sun

et al. 2010

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

In this paper, we propose a novel approach for high-dynamic-range (HDR) texture compression (TC) suitable for rendering systems of different capacities. Based on the previously proposed DHTC scheme, we first work out an improved joint-channel compression framework, which is robust and flexible enough to provide compressed HDR textures at different bit rates. Then, two compressed HDR texture formats based on the proposed framework are developed. The 8 bpp format is of near lossless visual quality, improving upon known state-of-the-art algorithms. And, to our knowledge, the 4 bpp format is the first workable 4 bpp solution with good quality. We also show that HDR textures in the proposed 4 bpp and 8 bpp formats can compose a layered architecture in the texture consumption pipeline, to significantly save the memory bandwidth and storage in real-time rendering. In addition, the 8 bpp format can also be used to handle traditional low dynamic range (LDR) RGBA textures. Our scheme exhibits a practical solution for compressing HDR textures at different rates and LDR textures with alpha maps.

show abstract

“…As a consequence, there is a growing demand for methods to reduce bandwidth consumption, even if that requires dedicated hardware logic. Texture compression, first introduced in 1996 [2] [3] [4], is the most prevalent manifestation of this approach in modern graphics processing units (GPUs).…”

Section: Introductionmentioning

confidence: 99%

Efficient floating-point texture decompression

Aarnio

Brunelli

Viitanen

2010

2010 International Symposium on System on Chip

View full text Add to dashboard Cite

We propose a novel hardware design for decoding compressed floating-point textures in a graphics processing unit (GPU). Our decoder is based on the NXR texture format, which provides lossy, fixed-rate 6:1 compression for floating-point textures. Our design exploits the constraints of the compressed pixel blocks to produce the correct output using only fixed-point arithmetic. This results in significantly lower silicon area occupation compared to pre-existing floating-point texture decoders.

show abstract

Hardware for superior texture performance

Cited by 31 publications

References 7 publications

A multiple representation data structure of 3D building textures

A multiple representation data structure of 3D building textures

High-Dynamic-Range Texture Compression for Rendering Systems of Different Capacities

Efficient floating-point texture decompression

Contact Info

Product

Resources

About