| [WORK IN PROGRESS] |
| |
| File: basis_spec.txt |
| Version 1.00 |
| |
| 1.0 Introduction |
| ---------------- |
| |
| The Basis Universal GPU texture codec supports reading and writing ".basis" files. |
| The .basis file format supports ETC1S or UASTC 4x4 texture data. |
| |
| * ETC1S is a simplified subset of ETC1. |
| |
| The mode is always differential (diff bit=1), the Rd, Gd, and Bd color deltas |
| are always (0,0,0), and the flip bit is always set. ETC1S texture data is fully |
| compliant with all existing software and hardware ETC1 decoders. Existing encoders |
| can be easily modified to limit their output to ETC1S. |
| |
| * UASTC 4x4 is a 19 mode subset of the ASTC texture format. Its specification is |
| [here](https://github.com/BinomialLLC/basis_universal/wiki/UASTC-Texture-Specification). UASTC texture data can always be losslessly transcoded to ASTC. |
| |
| 2.0 High-Level File Structure |
| ----------------------------- |
| |
| A .basis file consists of multiple sections. Apart from the header, which must always |
| be at the start of the file, the other sections may appear in any order. |
| |
| Here's the high level organization of a typical .basis file: |
| |
| * The file header |
| * Optional ETC1S compressed endpoint/selector codebooks |
| * Optional ETC1S Huffman table information |
| * A required "slice" description array describing the resolutions and file offset/compressed sizes of each texture slice present in the file |
| * 1 or more slices containing ETC1S or UASTC compressed texture data. |
| * For future expansion, the format supports an "extended" header which may be located anywhere in the file. This section contains .PNG-like chunked data. |
| |
| 3.0 File Enums |
| -------------- |
| |
| // basis_file_header::m_tex_type |
| enum basis_texture_type |
| { |
| cBASISTexType2D = 0, |
| cBASISTexType2DArray = 1, |
| cBASISTexTypeCubemapArray = 2, |
| cBASISTexTypeVideoFrames = 3, |
| cBASISTexTypeVolume = 4, |
| cBASISTexTypeTotal |
| }; |
| |
| // basis_slice_desc::flags |
| enum basis_slice_desc_flags |
| { |
| cSliceDescFlagsHasAlpha = 1, |
| cSliceDescFlagsFrameIsIFrame = 2 |
| }; |
| |
| // basis_file_header::m_tex_format enum basis_tex_format |
| { |
| cETC1S = 0, |
| cUASTC4x4 = 1 |
| }; |
| |
| // basis_file_header::m_flags enum basis_header_flags |
| { |
| cBASISHeaderFlagETC1S = 1. |
| cBASISHeaderFlagYFlipped = 2, |
| cBASISHeaderFlagHasAlphaSlices = 4 |
| }; |
| |
| |
| 4.0 File Structures |
| ------------------- |
| |
| All individual members in all file structures are byte aligned and little endian. The structs |
| have no padding (i.e. they are declared with #pragma pack(1)). |
| |
| 4.1 "basis_file_header" structure |
| --------------------------------- |
| |
| The file header must always be at the beginning of the file. |
| |
| struct basis_file_header |
| { |
| uint16 m_sig; // 2 byte file signature |
| uint16 m_ver; // File version |
| uint16 m_header_size; // Header size in bytes, sizeof(basis_file_header) or 0x4D |
| uint16 m_header_crc16; // CRC16/genibus of the remaining header data |
| |
| uint32 m_data_size; // The total size of all data after the header |
| uint16 m_data_crc16; // The CRC16 of all data after the header |
| |
| uint24 m_total_slices; // The number of compressed slices |
| uint24 m_total_images; // The total # of images |
| |
| byte m_tex_format; // enum basis_tex_format |
| uint16 m_flags; // enum basis_header_flags |
| byte m_tex_type; // enum basis_texture_type |
| uint24 m_us_per_frame; // Video: microseconds per frame |
| |
| uint32 m_reserved; // For future use |
| uint32 m_userdata0; // For client use |
| uint32 m_userdata1; // For client use |
| |
| uint16 m_total_endpoints; // ETC1S: The number of endpoints in the endpoint codebook |
| uint32 m_endpoint_cb_file_ofs; // ETC1S: The compressed endpoint codebook's file offset relative to the header |
| uint24 m_endpoint_cb_file_size; // ETC1S: The compressed endpoint codebook's size in bytes |
| |
| uint16 m_total_selectors; // ETC1S: The number of selectors in the selector codebook |
| uint32 m_selector_cb_file_ofs; // ETC1S: The compressed selector codebook's file offset relative to the header |
| uint24 m_selector_cb_file_size; // ETC1S: The compressed selector codebook's size in bytes |
| |
| uint32 m_tables_file_ofs; // ETC1S: The file offset of the compressed Huffman codelength tables. |
| uint32 m_tables_file_size; // ETC1S: The file size in bytes of the compressed Huffman codelength tables. |
| |
| uint32 m_slice_desc_file_ofs; // The file offset to the slice description array, usually follows the header |
| uint32 m_extended_file_ofs; // The file offset of the "extended" header and compressed data, for future use |
| uint32 m_extended_file_size; // The file size in bytes of the "extended" header and compressed data, for future use |
| }; |
| |
| 4.1.1 Details: |
| |
| * m_sig is always 'B' * 256 + 's', or 0x4273. |
| * m_ver is currently always 0x10. |
| * m_header_size is sizeof(basis_file_header). It's always 0x4D. |
| * m_header_crc16 is the CRC-16 of the remaining header data. See the "CRC-16" section for more information. |
| * m_data_size, m_data_crc16: The size of all data following the header, and its CRC-16. |
| * m_total_slices: The total number of slices, from [1,2^24-1] |
| * m_total_images: The total number of images (where one image can contain multiple mipmap levels, and each mipmap level is a different slice). |
| * m_tex_format: basis_tex_format. Either cETC1S (0), or cUASTC4x4 (1). |
| * m_flags: A combination of flags from the basis_header_flags enum. |
| * m_tex_type: The texture type, from enum basis_texture_type |
| * m_us_per_frame: Microseconds per frame, only valid for cBASISTexTypeVideoFrames texture types. |
| * m_total_endpoints, m_endpoint_cb_file_ofs, m_endpoint_cb_file_size: Information about the compressed ETC1S endpoint codebook: The total # of entries, the offset to the compressed data, and the compressed data's size. |
| * m_total_selectors, m_selector_cb_file_ofs, m_selector_cb_file_size: Information about the compressed ETC1S selector codebook: The total # of entries, the offset to the compressed data, and the compressed data's size. |
| * m_tables_file_ofs, m_tables_file_size: The file offset and size of the compressed Huffman tables for ETC1S format files. |
| * m_slice_desc_file_ofs: The file offset to the array of slice description structures. There will be m_total_slices structures at this file offset. |
| * m_extended_file_ofs, m_extended_file_size: The "extended" header, for future expansion. Currently unused. |
| |
| 4.2 "basis_slice_desc" structure |
| -------------------------------- |
| |
| struct basis_slice_desc |
| { |
| uint24 m_image_index; |
| uint8 m_level_index; |
| uint8 m_flags; |
| |
| uint16 m_orig_width; |
| uint16 m_orig_height; |
| |
| uint16 m_num_blocks_x; |
| uint16 m_num_blocks_y; |
| |
| uint32 m_file_ofs; |
| uint32 m_file_size; |
| |
| uint16 m_slice_data_crc16; |
| }; |
| |
| 4.2.1 Details: |
| |
| * m_image_index: The index of the source image provided to the encoder (will always appear in order from first to last, first image index is 0, no skipping allowed) |
| * m_level_index: The mipmap level index (mipmaps will always appear from largest to smallest) |
| * m_flags: enum basis_slice_desc_flags |
| * m_orig_width: The original image width (may not be a multiple of 4 pixels) |
| * m_orig_height: The original image height (may not be a multiple of 4 pixels) |
| * m_num_blocks_x: The slice's block X dimensions. Each block is 4x4 pixels. The slice's pixel resolution may or may not be a power of 2. |
| * m_num_blocks_y: The slice's block Y dimensions. |
| * m_file_ofs: Offset from the header to the start of the slice's data |
| * m_file_size: The size of the compressed slice data in bytes |
| * m_slice_data_crc16: The CRC16 of the compressed slice data, for extra-paranoid use cases |
| |
| 5.0 CRC-16 Function |
| ------------------- |
| |
| .basis files use CRC-16/genibus(aka CRC-16 EPC, CRC-16 I-CODE, CRC-16 DARC) format CRC-16's. |
| |
| Here's an example function in C++: |
| |
| uint16_t crc16(const void* r, size_t size, uint16_t crc) |
| { |
| crc = ~crc; |
| const uint8_t* p = static_cast<const uint8_t*>(r); |
| for ( ; size; --size) |
| { |
| const uint16_t q = *p++ ^ (crc >> 8); |
| uint16_t k = (q >> 4) ^ q; |
| crc = (((crc << 8) ^ k) ^ (k << 5)) ^ (k << 12); |
| } |
| |
| return static_cast<uint16_t>(~crc); |
| } |
| |
| This function is called with 0 in the final "crc" parameter when computing CRC-16's of file data. |
| |
| 6.0 Compressed Huffman Tables |
| ----------------------------- |
| |
| ETC1S format .basis files rely heavily on static [canonical Huffman |
| prefix coding](https://en.wikipedia.org/wiki/Canonical_Huffman_code). Multiple |
| Huffman tables are used by each compressed section. Huffman codes are stored in |
| each output byte in LSB to MSB order. (This is opposite of the JPEG format, |
| which stores the codes in MSB to LSB order.) |
| |
| Huffman coding in .basis is compatible with the canonical Huffman methods used |
| by Deflate encoders/decoders. Section 3.2.2 of [Deflate - RFC |
| 1951](https://tools.ietf.org/html/rfc1951), which describes how to compute the |
| value of each Huffman code given an array of symbol codelengths. This document |
| assumes familiarity with how Huffman coding works in Deflate. |
| |
| First, some enums: |
| |
| enum |
| { |
| // Max supported Huffman code size is 16-bits |
| cHuffmanMaxSupportedCodeSize = 16, |
| |
| // The maximum number of symbols is 2^14 |
| cHuffmanMaxSymsLog2 = 14, |
| cHuffmanMaxSyms = 1 << cHuffmanMaxSymsLog2, |
| |
| // Small zero runs may range from 3-10 entries |
| cHuffmanSmallZeroRunSizeMin = 3, |
| cHuffmanSmallZeroRunSizeMax = 10, |
| cHuffmanSmallZeroRunExtraBits = 3, |
| |
| // Big zero runs may range from 11-138 entries |
| cHuffmanBigZeroRunSizeMin = 11, |
| cHuffmanBigZeroRunSizeMax = 138, |
| cHuffmanBigZeroRunExtraBits = 7, |
| |
| // Small non-zero runs may range from 3-6 entries |
| cHuffmanSmallRepeatSizeMin = 3, |
| cHuffmanSmallRepeatSizeMax = 6, |
| cHuffmanSmallRepeatExtraBits = 2, |
| |
| // Big non-zero run may range from 7-134 entries |
| cHuffmanBigRepeatSizeMin = 7, |
| cHuffmanBigRepeatSizeMax = 134, |
| cHuffmanBigRepeatExtraBits = 7, |
| |
| // There are a maximum of 21 symbols in a compressed Huffman code length table. |
| cHuffmanTotalCodelengthCodes = 21, |
| |
| // Symbols [0,16] indicate code sizes. Other symbols indicate zero runs or repeats: |
| cHuffmanSmallZeroRunCode = 17, |
| cHuffmanBigZeroRunCode = 18, |
| cHuffmanSmallRepeatCode = 19, |
| cHuffmanBigRepeatCode = 20 |
| }; |
| |
| A .basis Huffman table consists of 1 to cHuffmanMaxSyms symbols. Each compressed |
| Huffman table is described by an array of symbol code lengths in bits. |
| |
| The table's symbol code lengths are themselves RLE+Huffman coded, just like |
| Deflate. (Note this can be confusing to developers unfamiliar with Deflate.) |
| Each table begins with a small fixed header: |
| |
| 14 bits: total_used_syms [1, cHuffmanMaxSyms] |
| 5 bits: num_codelength_codes [1, cHuffmanTotalCodelengthCodes] |
| |
| Next, the code lengths for the small Huffman table which is used to send the compressed codelengths (and RLE/repeat codes) are sent uncompressed but in a reordered manner: |
| |
| 3*num_codelength_codes bits: Code size of each Huffman symbol for the compressed Huffman codelength table. |
| |
| These code lengths are sent in this order (to help reduce the number that must be sent): |
| |
| { |
| cHuffmanSmallZeroRunCode, cHuffmanBigZeroRunCode, cHuffmanSmallRepeatCode, cHuffmanBigRepeatCode, |
| 0, 8, 7, 9, 6, 0xA, 5, 0xB, 4, 0xC, 3, 0xD, 2, 0xE, 1, 0xF, 0x10 |
| }; |
| |
| A canonical Huffman decoding table (of up to 21 symbols) should be built from |
| these code lengths. Immediately following this data are the Huffman symbols |
| (sometimes intermixed with raw bits) which describe how to unpack the |
| codelengths of each symbol in the Huffman table: |
| |
| - Symbols [0,16] indicate a specific symbol code length in bits. |
| |
| - Symbol cHuffmanSmallZeroRunCode (17) indicates a short run of symbols with 0 bit code lengths. |
| cHuffmanSmallZeroRunExtraBits (3) bits are sent after this symbol, which indicates the run's size after adding the minimum size (cHuffmanSmallZeroRunSizeMin). |
| |
| - Symbol cHuffmanBigZeroRunCode (18) indicates a long run of symbols with 0 bit code lengths. |
| cHuffmanBigZeroRunExtraBits (7) bits are sent after this symbol, which indicates the run's size after adding the minimum size (cHuffmanBigZeroRunSizeMin) |
| |
| - Symbol cHuffmanSmallRepeatCode (19) indicates a short run of symbols that repeat the previous symbol's code length. |
| cHuffmanSmallRepeatExtraBits (2) bits are sent after this symbol, which indicates the number of times to repeat the previous symbol's code length, |
| after adding the minimum size (cHuffmanSmallRepeatSizeMin). |
| Cannot be the first symbol, and the previous symbol cannot have a code length of 0. |
| |
| - Symbol cHuffmanBigRepeatCode (20) indicates a short run of symbols that repeat the previous symbol's code length. |
| cHuffmanBigRepeatExtraBits (7) bits are sent after this symbol, which indicates the number of times to repeat the previous symbol's code length, |
| after adding the minimum size (cHuffmanBigRepeatSizeMin). |
| Cannot be the first symbol, and the previous symbol cannot have a code length of 0. |
| |
| There should be exactly total_used_syms code lengths stored in the compressed Huffman table. If not the stream is either corrupted or invalid. |
| |
| After all the symbol codelengths are uncompressed, the symbol codes can be computed and the canonical Huffman decoding tables can be built. |
| |
| 7.0 ETC1S Endpoint Codebooks |
| ---------------------------- |
| |
| The endpoint codebook section starts at file offset |
| basis_file_header::m_endpoint_cb_file_ofs and is m_endpoint_cb_file_size bytes |
| long. The endpoint codebook will have basis_file_header::m_total_endpoints total |
| entries. |
| |
| At the beginning of the compressed endpoint codebook section are four compressed |
| Huffman tables, stored using the procedure outlined in section 6.0. The Huffman tables |
| appear in this order: |
| |
| 1. color5_delta_model0 |
| 2. color5_delta_model1 |
| 3. color5_delta_model2 |
| 4. inten_delta_model |
| |
| Following the data for these Huffman tables is a single 1-bit code which |
| indicates if the color endpoint codebook is grayscale or not. |
| |
| Immediately following this code is the compressed color endpoint codebook data. |
| A simple form of DPCM coding is used to send the ETC1S intensity table indices and |
| color values. Here is the procedure to decode the endpoint codebook: |
| |
| const int COLOR5_PAL0_PREV_HI = 9, COLOR5_PAL0_DELTA_LO = -9, COLOR5_PAL0_DELTA_HI = 31; |
| const int COLOR5_PAL1_PREV_HI = 21, COLOR5_PAL1_DELTA_LO = -21, COLOR5_PAL1_DELTA_HI = 21; |
| const int COLOR5_PAL2_PREV_HI = 31, COLOR5_PAL2_DELTA_LO = -31, COLOR5_PAL2_DELTA_HI = 9; |
| |
| // Assume previous endpoint color is (16, 16, 16), and the previous intensity is 0. |
| color32 prev_color5(16, 16, 16, 0); |
| uint32_t prev_inten = 0; |
| |
| // For each endpoint codebook entry |
| for (uint32_t i = 0; i < num_endpoints; i++) |
| { |
| // Decode the intensity delta Huffman code |
| uint32_t inten_delta = sym_codec.decode_huffman(inten_delta_model); |
| m_endpoints[i].m_inten5 = static_cast<uint8_t>((inten_delta + prev_inten) & 7); |
| prev_inten = m_endpoints[i].m_inten5; |
| |
| // Now decode the endpoint entry's color or intensity value |
| for (uint32_t c = 0; c < (endpoints_are_grayscale ? 1U : 3U); c++) |
| { |
| // The Huffman table we used to decode the delta depends on the previous color's value |
| int delta; |
| if (prev_color5[c] <= basist::COLOR5_PAL0_PREV_HI) |
| delta = sym_codec.decode_huffman(color5_delta_model0); |
| else if (prev_color5[c] <= basist::COLOR5_PAL1_PREV_HI) |
| delta = sym_codec.decode_huffman(color5_delta_model1); |
| else |
| delta = sym_codec.decode_huffman(color5_delta_model2); |
| |
| // Apply the delta |
| int v = (prev_color5[c] + delta) & 31; |
| |
| m_endpoints[i].m_color5[c] = static_cast<uint8_t>(v); |
| |
| prev_color5[c] = static_cast<uint8_t>(v); |
| } |
| |
| // If the endpoints are grayscale, set G and B to match R. |
| if (endpoints_are_grayscale) |
| { |
| m_endpoints[i].m_color5[1] = m_endpoints[i].m_color5[0]; |
| m_endpoints[i].m_color5[2] = m_endpoints[i].m_color5[0]; |
| } |
| } |
| |
| The rest of the section's data (if any) can be ignored. |
| |
| 8.0 ETC1S Selector Codebooks |
| ---------------------------- |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |