oidn-web 0.2.1 → 0.2.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +11 -1
  2. package/package.json +3 -1
  3. /package/dist/{oidn.mjs → oidn.js} +0 -0
  4. /package/dist/{oidn.umd.js → oidn.umd.cjs} +0 -0
package/README.md CHANGED
@@ -2,7 +2,11 @@
2
2
 
3
3
  This library brings the state-of-the-art AI-based denoising library [Open Image Denoise](https://github.com/RenderKit/oidn) to the web.
4
4
 
5
- Many thanks to Max Liani for his series https://maxliani.wordpress.com/2023/03/17/dnnd-1-a-deep-neural-network-dive/. My work is mostly inspired by it.
5
+ It's used in the [Vector to 3D](https://www.figma.com/community/plugin/1264600219316901594/) Figma plugin for high quality rendering and denoising.
6
+
7
+ | 2000 Samples | 3 Samples | 3 Samples + Denoised |
8
+ | :----------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------: |
9
+ | ![](https://github.com/pissang/oidn-web/blob/main/examples/test/ground-truth.png 'Ground Truth') | ![](https://github.com/pissang/oidn-web/blob/main/examples/test/noisy.png 'Noisy') | ![](https://github.com/pissang/oidn-web/blob/main/examples/test/denoised.png 'Denoised') |
6
10
 
7
11
  ## How it Works.
8
12
 
@@ -98,6 +102,8 @@ initUNetFromURL('./weights/rt_hdr_alb_nrm.tza', undefined, {
98
102
 
99
103
  If you already have a WebGPU path tracer. You can integrate the oidn-web into your pipeline. It supports input/output gpu buffers to avoid the cost of syncing between CPU and GPU.
100
104
 
105
+ `hdr` and `aux` are required in the WebGPU pipeline.
106
+
101
107
  ```ts
102
108
  initUNetFromURL(
103
109
  './weights/rt_hdr_alb_nrm.tza',
@@ -143,3 +149,7 @@ initUNetFromURL('./weights/rt_hdr_alb_nrm_small.tza', ...);
143
149
  ```
144
150
 
145
151
  Other combinations can be found in the [oidn-weights](https://github.com/RenderKit/oidn-weights)
152
+
153
+ ## Credits
154
+
155
+ Huge thanks to Max Liani for his series: https://maxliani.wordpress.com/2023/03/17/dnnd-1-a-deep-neural-network-dive/. My work is mostly inspired by it.
package/package.json CHANGED
@@ -1,8 +1,10 @@
1
1
  {
2
2
  "name": "oidn-web",
3
- "version": "0.2.1",
3
+ "version": "0.2.2",
4
4
  "description": "Run Open Image Denoiser on the Web",
5
5
  "main": "lib/main.js",
6
+ "types": "lib/main.d.ts",
7
+ "type": "module",
6
8
  "scripts": {
7
9
  "build": "vite build",
8
10
  "dev": "vite dev",
/package/dist/{oidn.mjs → oidn.js} RENAMED
File without changes
/package/dist/{oidn.umd.js → oidn.umd.cjs} RENAMED
File without changes