<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
	<id>https://wiki.selur.net/index.php?action=history&amp;feed=atom&amp;title=Vapoursynth_BasicVSR%2B%2B</id>
	<title>Vapoursynth BasicVSR++ - Revision history</title>
	<link rel="self" type="application/atom+xml" href="https://wiki.selur.net/index.php?action=history&amp;feed=atom&amp;title=Vapoursynth_BasicVSR%2B%2B"/>
	<link rel="alternate" type="text/html" href="https://wiki.selur.net/index.php?title=Vapoursynth_BasicVSR%2B%2B&amp;action=history"/>
	<updated>2026-11-19T08:13:21Z</updated>
	<subtitle>Revision history for this page on the wiki</subtitle>
	<generator>MediaWiki 1.46.2</generator>
	<entry>
		<id>https://wiki.selur.net/index.php?title=Vapoursynth_BasicVSR%2B%2B&amp;diff=463&amp;oldid=prev</id>
		<title>Selur: New filter page (via create-page on MediaWiki MCP Server)</title>
		<link rel="alternate" type="text/html" href="https://wiki.selur.net/index.php?title=Vapoursynth_BasicVSR%2B%2B&amp;diff=463&amp;oldid=prev"/>
		<updated>2026-11-16T08:47:30Z</updated>

		<summary type="html">&lt;p&gt;New filter page (via create-page on MediaWiki MCP Server)&lt;/p&gt;
&lt;p&gt;&lt;b&gt;New page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;&amp;lt;div style=&amp;quot;float:right; margin:0 0 1em 1em;&amp;quot;&amp;gt;__TOC__&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039;BasicVSR++&amp;#039;&amp;#039;&amp;#039; is a recurrent video network that uses neighbor frames to restore each frame; this filter offers its models for compressed-video enhancement, deblurring and denoising at the input size. It runs on an NVIDIA GPU through PyTorch; the 4× super-resolution models are in [[Vapoursynth BasicVSR++ Resize]].&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;Filtering → Vapoursynth → Other&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
[[File:Vapoursynth_BasicVSRPP.png|none|BasicVSR++ controls in Hybrid]]&lt;br /&gt;
&lt;br /&gt;
== What it does ==&lt;br /&gt;
Frames are processed in sequences of &amp;#039;&amp;#039;Length&amp;#039;&amp;#039; frames; information is carried forward and backward through each sequence and aligned with optical flow. The result of a frame therefore depends on its neighbors, not only on the frame itself. The output keeps the input size.&lt;br /&gt;
&lt;br /&gt;
== Requirements ==&lt;br /&gt;
* Windows, Hybrid&amp;#039;s torch add-on and an NVIDIA GPU with CUDA.&lt;br /&gt;
&lt;br /&gt;
== Settings ==&lt;br /&gt;
{| class=&amp;quot;wikitable&amp;quot;&lt;br /&gt;
! Control !! Parameter !! Range / values !! Hybrid default !! Meaning&lt;br /&gt;
|-&lt;br /&gt;
| Model || model || NTIRE 2021 (1), (2), (3), Video Deblurring (DVD), Video Deblurring (GoPro), Video Denoising || NTIRE 2021 (1) || Network; the NTIRE 2021 models are the three tracks of the challenge on quality enhancement of compressed video.&lt;br /&gt;
|-&lt;br /&gt;
| Length || length || 1 – 1000 || 15 || Frames per processed sequence; more frames need more GPU memory.&lt;br /&gt;
|-&lt;br /&gt;
| Device || device_index || 0 – 4 || 0 || CUDA device.&lt;br /&gt;
|-&lt;br /&gt;
| Tile (x/y) || tile || 0 – 8192 || 0 / 0 || Splits the frame into tiles to save GPU memory; 0 = no tiling (both values must be set).&lt;br /&gt;
|-&lt;br /&gt;
| Tile pad || tile_pad || 0 – 64 || 16 || Overlap of the tiles; only with tiling.&lt;br /&gt;
|-&lt;br /&gt;
| FP16 || – || on/off || off || Half precision (16-bit float clip); faster and needs less memory.&lt;br /&gt;
|-&lt;br /&gt;
| CPU Cache || cpu_cache || on/off || off || Keeps intermediate features in system RAM; saves GPU memory, slower.&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Example ==&lt;br /&gt;
Default settings on a 10-bit YUV 4:2:0 source (640x356):&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
clip = core.std.AddBorders(clip=clip, left=0, right=0, top=2, bottom=2) # add borders to achieve mod 8 (vsBasicVSRPPFilter) - 640x360&lt;br /&gt;
# adjusting color space from YUV420P10 to RGBS for vsBasicVSRPPFilter&lt;br /&gt;
clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s=&amp;quot;470bg&amp;quot;, range_in_s=&amp;quot;limited&amp;quot;, range_s=&amp;quot;full&amp;quot;)&lt;br /&gt;
# Quality enhancement using BasicVSR++&lt;br /&gt;
from vsbasicvsrpp import basicvsrpp as BasicVSRPP&lt;br /&gt;
clip = BasicVSRPP(clip, model=4)&lt;br /&gt;
clip = core.std.Crop(clip=clip, left=0, right=0, top=2, bottom=2) # removing added borders from mod requirement (vsBasicVSRPPFilter) -  640x356&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
== How Hybrid calls it ==&lt;br /&gt;
* The clip is converted to 32-bit float RGB (16-bit float with FP16) and padded to mod 8; the padding is cropped afterwards.&lt;br /&gt;
* The model is always written; length, device, tiles and tile pad only when they differ from the defaults.&lt;br /&gt;
* BasicVSR++ also offers the [[Vapoursynth common filter options|common options]] (Masked, ApplyOnlyTo, Merge, OnRegion, Gimmick).&lt;br /&gt;
&lt;br /&gt;
== Background ==&lt;br /&gt;
=== BasicVSR++ ===&lt;br /&gt;
BasicVSR++ (Chan et al., CVPR 2022) improves BasicVSR with second-order grid propagation and flow-guided deformable alignment. It won tracks of the NTIRE 2021 challenges on video super-resolution and on compressed video enhancement.&lt;br /&gt;
&lt;br /&gt;
=== vs-basicvsrpp ===&lt;br /&gt;
HolyWu&amp;#039;s vs-basicvsrpp runs BasicVSR++ in VapourSynth with PyTorch and accepts 16- or 32-bit float RGB. It processes &amp;#039;&amp;#039;Length&amp;#039;&amp;#039; frames per call and keeps them in a cache, so playing or encoding front to back is much faster than jumping around in the clip.&lt;br /&gt;
&lt;br /&gt;
== Sources ==&lt;br /&gt;
* [https://github.com/HolyWu/vs-basicvsrpp vs-basicvsrpp]&lt;br /&gt;
* [https://github.com/ckkelvinchan/BasicVSR_PlusPlus BasicVSR++]&lt;br /&gt;
* Hybrid&amp;#039;s tooltips&lt;br /&gt;
&lt;br /&gt;
[[Category:Vapoursynth Filters]]&lt;/div&gt;</summary>
		<author><name>Selur</name></author>
	</entry>
</feed>