curioustorvald/tsvm
1
0
Fork 0
mirror of https://github.com/curioustorvald/tsvm.git synced 2026-03-07 19:51:51 +09:00
Code Issues Packages Projects Releases Wiki Activity

TAV: now writes encoder q-value to the header

Browse Source
This commit is contained in:
minjaesong
2025-09-25 18:15:53 +09:00
parent ca18595134
commit 4d9981ec23
4 changed files with 40 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
assets/disk0/tvdos/bin/playtav.js
View File

@@ -375,7 +375,8 @@ let header = {
qualityCg: 0, // TAV-specific: Cg channel quality
extraFlags: 0,
videoFlags: 0,
reserved: new Array(7)
qualityLevel: 0,
fileRole: 0
}
// Read and validate header
@@ -410,11 +411,11 @@ header.qualityCo = seqread.readOneByte()
header.qualityCg = seqread.readOneByte()
header.extraFlags = seqread.readOneByte()
header.videoFlags = seqread.readOneByte()
header.qualityLevel = seqread.readOneByte() // the decoder expects biased value
header.fileRole = seqread.readOneByte()
// Skip reserved bytes
for (let i = 0; i < 7; i++) {
seqread.readOneByte()
}
seqread.skip(5)
if (header.version < 1 || header.version > 6) {
printerrln(`Error: Unsupported TAV version ${header.version}`)
@@ -710,7 +711,7 @@ try {
blockDataPtr,
CURRENT_RGB_ADDR, PREV_RGB_ADDR, // RGB buffer pointers (not float arrays!)
header.width, header.height,
header.qualityY, header.qualityCo, header.qualityCg,
header.qualityLevel, header.qualityY, header.qualityCo, header.qualityCg,
frameCount,
header.waveletFilter, // TAV-specific parameter
header.decompLevels, // TAV-specific parameter

3
terranmon.txt
View File

@@ -915,12 +915,13 @@ transmission capability, and region-of-interest coding.
- bit 1 = is NTSC framerate
- bit 2 = is lossless mode
- bit 3 = has region-of-interest coding (for still images only)
uint8 Encoder quality level (stored with bias of 1 (q0=1); used to derive anisotropy value)
uint8 File Role
- 0 = generic
- 1 = this file is header-only, and UCF payload will be followed (used by seekable movie file)
When header-only file contain video packets, they should be presented as an Intro Movie
before the user-interactable selector (served by the UCF payoad)
uint8 Reserved[6]: fill with zeros
uint8 Reserved[5]: fill with zeros
## Packet Types
0x10: I-frame (intra-coded frame)

41
tsvm_core/src/net/torvald/tsvm/GraphicsJSR223Delegate.kt
View File

@@ -4128,17 +4128,22 @@ class GraphicsJSR223Delegate(private val vm: VM) {
private val FOUR_PIXEL_DETAILER = 0.88f
private val TWO_PIXEL_DETAILER = 0.92f
// level is one-based index
private fun getPerceptualWeight(qYGlobal: Int, level: Int, subbandType: Int, isChroma: Boolean, maxLevels: Int): Float {
// Psychovisual model based on DWT coefficient statistics and Human Visual System sensitivity
val qualityLevel = if (qYGlobal >= 60) 0
private fun tavDeriveEncoderQindex(qIndex: Int, qYGlobal: Int): Int {
if (qIndex > 0) return qIndex - 1
return if (qYGlobal >= 60) 0
else if (qYGlobal >= 42) 1
else if (qYGlobal >= 25) 2
else if (qYGlobal >= 12) 3
else if (qYGlobal >= 6) 4
else if (qYGlobal >= 2) 5
else 5
}
// level is one-based index
private fun getPerceptualWeight(qIndex: Int, qYGlobal: Int, level: Int, subbandType: Int, isChroma: Boolean, maxLevels: Int): Float {
// Psychovisual model based on DWT coefficient statistics and Human Visual System sensitivity
val qualityLevel = tavDeriveEncoderQindex(qIndex, qYGlobal)
if (!isChroma) {
// LUMA CHANNEL: Based on statistical analysis from real video content
@@ -4192,7 +4197,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
return "min=$min, Q1=$q1, med=%.1f, Q3=$q3, max=$max, n=$n".format(median)
}
private fun dequantiseDWTSubbandsPerceptual(qYGlobal: Int, quantised: ShortArray, dequantised: FloatArray,
private fun dequantiseDWTSubbandsPerceptual(qIndex: Int, qYGlobal: Int, quantised: ShortArray, dequantised: FloatArray,
subbands: List<DWTSubbandInfo>, baseQuantizer: Float, isChroma: Boolean, decompLevels: Int) {
// Initialise output array to zero (critical for detecting missing coefficients)
@@ -4205,7 +4210,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
var maxIdx = -1
for (subband in subbands) {
val weight = getPerceptualWeight(qYGlobal, subband.level, subband.subbandType, isChroma, decompLevels)
val weight = getPerceptualWeight(qIndex, qYGlobal, subband.level, subband.subbandType, isChroma, decompLevels)
// CRITICAL FIX: Use the same effective quantizer as encoder for proper reconstruction
val effectiveQuantizer = baseQuantizer * weight
@@ -4266,7 +4271,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
private var tavDebugCurrentFrameNumber = 0
fun tavDecode(blockDataPtr: Long, currentRGBAddr: Long, prevRGBAddr: Long,
width: Int, height: Int, qYGlobal: Int, qCoGlobal: Int, qCgGlobal: Int, frameCount: Int,
width: Int, height: Int, qIndex: Int, qYGlobal: Int, qCoGlobal: Int, qCgGlobal: Int, frameCount: Int,
waveletFilter: Int = 1, decompLevels: Int = 6, isLossless: Boolean = false, tavVersion: Int = 1) {
tavDebugCurrentFrameNumber = frameCount
@@ -4314,13 +4319,13 @@ class GraphicsJSR223Delegate(private val vm: VM) {
}
0x01 -> { // TAV_MODE_INTRA
// Decode DWT coefficients directly to RGB buffer
readPtr = tavDecodeDWTIntraTileRGB(qYGlobal, readPtr, tileX, tileY, currentRGBAddr,
readPtr = tavDecodeDWTIntraTileRGB(qIndex, qYGlobal, readPtr, tileX, tileY, currentRGBAddr,
width, height, qY, qCo, qCg,
waveletFilter, decompLevels, isLossless, tavVersion, isMonoblock)
}
0x02 -> { // TAV_MODE_DELTA
// Coefficient delta encoding for efficient P-frames
readPtr = tavDecodeDeltaTileRGB(qYGlobal, readPtr, tileX, tileY, currentRGBAddr,
readPtr = tavDecodeDeltaTileRGB(readPtr, tileX, tileY, currentRGBAddr,
width, height, qY, qCo, qCg,
waveletFilter, decompLevels, isLossless, tavVersion, isMonoblock)
}
@@ -4333,7 +4338,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
}
}
private fun tavDecodeDWTIntraTileRGB(qYGlobal: Int, readPtr: Long, tileX: Int, tileY: Int, currentRGBAddr: Long,
private fun tavDecodeDWTIntraTileRGB(qIndex: Int, qYGlobal: Int, readPtr: Long, tileX: Int, tileY: Int, currentRGBAddr: Long,
width: Int, height: Int, qY: Int, qCo: Int, qCg: Int,
waveletFilter: Int, decompLevels: Int, isLossless: Boolean, tavVersion: Int, isMonoblock: Boolean = false): Long {
// Determine coefficient count based on mode
@@ -4393,9 +4398,9 @@ class GraphicsJSR223Delegate(private val vm: VM) {
val tileHeight = if (isMonoblock) height else PADDED_TILE_SIZE_Y
val subbands = calculateSubbandLayout(tileWidth, tileHeight, decompLevels)
dequantiseDWTSubbandsPerceptual(qYGlobal, quantisedY, yTile, subbands, qY.toFloat(), false, decompLevels)
dequantiseDWTSubbandsPerceptual(qYGlobal, quantisedCo, coTile, subbands, qCo.toFloat(), true, decompLevels)
dequantiseDWTSubbandsPerceptual(qYGlobal, quantisedCg, cgTile, subbands, qCg.toFloat(), true, decompLevels)
dequantiseDWTSubbandsPerceptual(qIndex, qYGlobal, quantisedY, yTile, subbands, qY.toFloat(), false, decompLevels)
dequantiseDWTSubbandsPerceptual(qIndex, qYGlobal, quantisedCo, coTile, subbands, qCo.toFloat(), true, decompLevels)
dequantiseDWTSubbandsPerceptual(qIndex, qYGlobal, quantisedCg, cgTile, subbands, qCg.toFloat(), true, decompLevels)
// Debug: Check coefficient values before inverse DWT
if (tavDebugCurrentFrameNumber == tavDebugFrameTarget) {
@@ -5036,7 +5041,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
return 1.0f
}
private fun tavDecodeDeltaTileRGB(qYGlobal: Int, readPtr: Long, tileX: Int, tileY: Int, currentRGBAddr: Long,
private fun tavDecodeDeltaTileRGB(readPtr: Long, tileX: Int, tileY: Int, currentRGBAddr: Long,
width: Int, height: Int, qY: Int, qCo: Int, qCg: Int,
waveletFilter: Int, decompLevels: Int, isLossless: Boolean, tavVersion: Int, isMonoblock: Boolean = false): Long {
@@ -5274,8 +5279,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
// return 1f
return when(level) {
0 -> 6f/5f
1 -> 5f/5f
2 -> 5f/6f
1 -> 5f/6f
else -> 1f
}
}
@@ -5286,8 +5290,7 @@ class GraphicsJSR223Delegate(private val vm: VM) {
// return 1f
return when (level) {
0 -> 6f/5f
1 -> 5f/5f
2 -> 5f/6f
1 -> 5f/6f
else -> 1f
}
}

6
video_encoder/encoder_tav.c
View File

@@ -1606,8 +1606,10 @@ static int write_tav_header(tav_encoder_t *enc) {
if (enc->lossless) video_flags |= 0x04; // Lossless
fputc(video_flags, enc->output_fp);
// Reserved bytes (7 bytes)
for (int i = 0; i < 7; i++) {
fputc(enc->quality_level+1, enc->output_fp);
// Reserved bytes (6 bytes)
for (int i = 0; i < 6; i++) {
fputc(0, enc->output_fp);
}