![]() ![]() I suspect the face is upscale with GFPGAN, while the background is upscale with Real-ESRGAN ? The Face Model generally give excellent result on tiny face. (There will be Mac version but ETA unknown.) No auto Preview, you have click the Preview button every time and it will process the whole picture.Īt the moment, only Windows version. (For JPG, It always output at 100% quality). No way to select export image format or compression. Using the General Model, the background upscale nicely but the face will be distorted. Using Face Model, enhance the face nicely but the background detail will be all removed. It will be challenging if a photo contain both person & landscape. There are 3 AI models available, but there is no way to adjust the level of noise reduction or sharpness. There is no way to input scale factor or dimension. It's extraordinary what modern software can do with low-quality legacy footage.After some testing, I would like to summarize what I have found. ![]() It allowed me to do clip-level colour grading on the entire five minute show. It auto-selected my GPU and my system rendered the above DV footage at about 5 fps, content-dependent.Įqually satisfying was the "timeline/auto detect cuts" function in Resolve, which worked flawlessly on this first-time attempt. This software has been criticized for being slow to render. I restored a finished five minute AVI from a Discreet Edit system and upscaled the original interlaced 720X480 to progressive 1280X960.ĭe-noise was very effective, removing nearly all the (horrendous) noise from an available light, after-dark 757 cockpit sequence. ![]() I saw the same artifacts mentioned above when the software encountered rapid motion, but overall the restoration and upscaling was excellent. My first attempts yesterday at restoring early 90s consumer DV footage were quite successful. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |