lucataco/depth-anything-video-sbs 🔢🖼️❓ → 🖼️

▶️ 209 runs 📅 Feb 2024 ⚙️ Cog 0.9.3 🔗 GitHub
stereoscopic-3d video-to-video

About

POC implementation of Depth-anything to produce a 3D SBS video

Example Output

Output

Performance Metrics

104.39s Prediction Time
104.46s Total Time
All Input Parameters
{
  "ipd": 6.34,
  "video": "https://replicate.delivery/pbxt/KSF1kXgU3qDkCwcH24bBK1LeNUu3J7AUtuXSbxqk8K43Y6ZC/wooly-720p.mp4",
  "encoder": "vits"
}
Input Parameters
ipd Type: numberDefault: 6.34
Interpupillary distance
video (required) Type: string
Input video
encoder Default: vits
Model type
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Processing depth frames /tmp/tmpdznn39ecwooly-720p.mp4
/root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
warnings.warn(
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil      56. 70.100 / 56. 70.100
libavcodec     58.134.100 / 58.134.100
libavformat    58. 76.100 / 58. 76.100
libavdevice    58. 13.100 / 58. 13.100
libavfilter     7.110.100 /  7.110.100
libswscale      5.  9.100 /  5.  9.100
libswresample   3.  9.100 /  3.  9.100
libpostproc    55.  9.100 / 55.  9.100
Input #0, image2, from '/tmp/stereo/%d.jpg':
Duration: 00:00:12.00, start: 0.000000, bitrate: N/A
Stream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 2560x720 [SAR 1:1 DAR 32:9], 25 fps, 25 tbr, 25 tbn, 25 tbc
Stream mapping:
Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[swscaler @ 0x55f449d96b80] deprecated pixel format used, make sure you did set range correctly
[libx264 @ 0x55f449bb6800] using SAR=1/1
[libx264 @ 0x55f449bb6800] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x55f449bb6800] profile High, level 4.0, 4:2:0, 8-bit
[libx264 @ 0x55f449bb6800] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=15 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
Output #0, mp4, to '/tmp/output.mp4':
Metadata:
encoder         : Lavf58.76.100
Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 2560x720 [SAR 1:1 DAR 32:9], q=2-31, 30 fps, 15360 tbn
Metadata:
encoder         : Lavc58.134.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A
frame=    1 fps=0.0 q=0.0 size=       0kB time=00:00:00.00 bitrate=N/A speed=N/A
frame=   45 fps=0.0 q=0.0 size=       0kB time=00:00:00.00 bitrate=N/A speed=   0x
frame=   78 fps= 77 q=29.0 size=     512kB time=00:00:00.53 bitrate=7864.1kbits/s speed=0.528x
frame=  123 fps= 81 q=29.0 size=    1280kB time=00:00:02.03 bitrate=5157.0kbits/s speed=1.34x
frame=  168 fps= 83 q=29.0 size=    2048kB time=00:00:03.53 bitrate=4748.3kbits/s speed=1.75x
frame=  212 fps= 84 q=29.0 size=    2816kB time=00:00:05.00 bitrate=4613.8kbits/s speed=1.98x
frame=  256 fps= 85 q=29.0 size=    3840kB time=00:00:06.46 bitrate=4864.5kbits/s speed=2.13x
frame=  296 fps= 83 q=26.0 size=    4864kB time=00:00:07.80 bitrate=5108.5kbits/s speed=2.19x
frame=  300 fps= 76 q=-1.0 Lsize=    6486kB time=00:00:09.90 bitrate=5366.9kbits/s speed=2.49x
video:6481kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.068886%
[libx264 @ 0x55f449bb6800] frame I:2     Avg QP:21.73  size:306198
[libx264 @ 0x55f449bb6800] frame P:76    Avg QP:23.74  size: 63982
[libx264 @ 0x55f449bb6800] frame B:222   Avg QP:28.58  size:  5231
[libx264 @ 0x55f449bb6800] consecutive B-frames:  1.3%  0.0%  0.0% 98.7%
[libx264 @ 0x55f449bb6800] mb I  I16..4: 14.3% 55.8% 29.9%
[libx264 @ 0x55f449bb6800] mb P  I16..4:  1.8%  2.6%  0.6%  P16..4: 39.0% 22.6% 18.1%  0.0%  0.0%    skip:15.3%
[libx264 @ 0x55f449bb6800] mb B  I16..4:  0.0%  0.0%  0.0%  B16..8: 32.8%  2.8%  0.6%  direct: 0.9%  skip:62.8%  L0:45.2% L1:46.0% BI: 8.8%
[libx264 @ 0x55f449bb6800] 8x8 transform intra:53.5% inter:55.8%
[libx264 @ 0x55f449bb6800] coded y,uvDC,uvAC intra: 49.5% 52.0% 8.4% inter: 12.1% 5.8% 0.0%
[libx264 @ 0x55f449bb6800] i16 v,h,dc,p: 15% 31% 10% 44%
[libx264 @ 0x55f449bb6800] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 18% 17% 28%  4%  7%  8%  7%  5%  7%
[libx264 @ 0x55f449bb6800] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 17% 17% 11%  5% 12% 11% 11%  7%  8%
[libx264 @ 0x55f449bb6800] i8c dc,h,v,p: 56% 23% 17%  4%
[libx264 @ 0x55f449bb6800] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x55f449bb6800] ref P L0: 55.8% 17.3% 19.9%  6.9%
[libx264 @ 0x55f449bb6800] ref B L0: 90.7%  8.0%  1.3%
[libx264 @ 0x55f449bb6800] ref B L1: 97.2%  2.8%
[libx264 @ 0x55f449bb6800] kb/s:5309.08
Time taken for the whole run: 101.9380567073822 seconds
Version Details
Version ID
4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455
Version Created
February 23, 2024
Run on Replicate →