Variable Bit Rate GPU Texture Decompression

Abstract

a) Raw textures (167.7 MB) (b) VBR textures (14.9 MB) Figure 1: Variable bit rate texture compression applied to the Napoleon Bonaparte scene from Sid Meier's Civilization R V using 27 textures. Image (b) using VBR compressed textures has a Mean SSIM error of 0.9935 (best=1) and SHAME-II color difference of 0.539 (best=0) compared to Image (a) using raw uncompressed textures. AbstractVariable bit rate compression can achieve better quality and compression rates than fixed bit rate methods. None the less, GPU texturing uses lossy fixed bit rate methods like DXT to allow random access and on-the-fly decompression during rendering. Changes in games and GPUs since DXT was developed make its compression artifacts less acceptable, and texture bandwidth less of an issue, but texture size is a serious and growing problem. Games use a large total volume of texture data, but have a much smaller active set. We present a new paradigm that separates GPU decompression from rendering. Rendering is from uncompressed data, avoiding the need for random access decompression. We demonstrate this paradigm with a new variable bit rate lossy texture compression algorithm that is well suited to the GPU, including a new GPU-friendly formulation of range decoding, and a new texture compression scheme averaging 12.4:1 lossy compression ratio on 471 real game textures with a quality level similar to traditional DXT compression. The total game texture set are stored in the GPU in compressed form, and decompressed for use in a fraction of a second per scene.

VBTC: GPU‐Friendly Variable Block Size Texture Encoding

“…[OBGB11]. The designations v1, v2 and v3 are used to match those presented in the paper [OBGB11]. (middle) The same comparison across all images from the Kodak Test Image Suite [KOD99].…”

“…al. using a range coder and decompressing them in a shader program on the GPU [OBGB11]. This compression scheme uses texture mipmap levels to predict the higher resolution colors and encodes the prediction error.…”

Texture Compression using Wavelet Decomposition

“…The energy compaction properties of the DCT and DWT are widely known and have been used in state of the art image coders, but as noted in the introduction, such codecs are impractical for texture compression. Nevertheless, variations of these codecs are used in texture streaming solutions [vW06] [OBGB11], where the entropy encoded textures are decompressed to the graphics memory before the actual rendering. The application of wavelets to texture compression has been explored before in [DCH05] and [Bou08], where the typical entropy encoding step is skipped and the most important wavelet coefficients are stored in a tree for fast random access, but the method does not produce significantly better results than S3TC, and requires a tree traversal for each texel fetch.…”

Evaluating Texture Compression Masking Effects Using Objective Image Quality Assessment Metrics

“…Current GPU compression algorithms use fixed bit-rates [1], [2] and recent research has explored reducing the bit rate [3], [4] as well as using variable bit-rate algorithms [5], [6].…”