DoubangoTelecom/compv

View on GitHub

Insanely fast Open Source Computer Vision library for ARM and x86 devices (Up to #50 times faster than OpenCV)

Stars: 212
Forks: 47
Open beginner issues: 0
Indexed issues: 143

Dominant language: C++
License: GPL-3.0
Last GitHub push: Jul 30, 2026
Latest indexed: Sep 15, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

143 issues indexed so far

Find efficient way to malloc, realloc, and calloc aligned memory on all platforms Open

DoubangoTelecom/compv#1 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
reallocAligned not optimized (free old then alloc new) Open

DoubangoTelecom/compv#3 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
CompVThread::setAffinity not implemented on OSX and iOS Open

DoubangoTelecom/compv#4 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
CompVThread::setAffinity not tested on Android Open

DoubangoTelecom/compv#5 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
AVX-SSE Transition Penalties Open

DoubangoTelecom/compv#6 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
replace _mm256_permute4x64_epi64 with _mm256_shuffle_epi8 Open

DoubangoTelecom/compv#7 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Most of the asm code could be opti for x64 (remove, pushs, remove allocation, remove saving/restoring xmm/ymm registers...) Open

DoubangoTelecom/compv#8 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Align the data and stride on the cache line size if it's <128 and pow2(must be but who knows). Open

DoubangoTelecom/compv#9 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
FAST detector: add support for both SAD and maxThreshold in NMS Open

DoubangoTelecom/compv#11 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Convert SSSE3 functions to SSE2 when possible Open

DoubangoTelecom/compv#12 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Add support for DCCI interpolation (preserve edges) Open

DoubangoTelecom/compv#14 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Create Doubango feature detector+descriptor Open

DoubangoTelecom/compv#15 · 12 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Add support for PROSAC Open

DoubangoTelecom/compv#16 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
implement fastArctan2 for embedded devices Open

DoubangoTelecom/compv#17 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Add support for Apple's accelerate framework Open

DoubangoTelecom/compv#18 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Review all x86/x64 assemply using Intel Optimization manual Open

DoubangoTelecom/compv#19 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Use SpinWait in asynTask Open

DoubangoTelecom/compv#20 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
COMPV_XXXXX_MIN_SAMPLES_PER_THREAD macros must depends on the CPU hz Open

DoubangoTelecom/compv#21 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Always use 'lea edi, [edi +4]' instead of 'add edi, 4' Open

DoubangoTelecom/compv#22 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
add support video feature detection and description: motion estimation and compensation Open

DoubangoTelecom/compv#23 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Do not use WaitForSingleObject for multithreading: performance issues Open

DoubangoTelecom/compv#24 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Use letsencrypt.org to secure compv.org Open

DoubangoTelecom/compv#26 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Products Open

DoubangoTelecom/compv#29 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Use valgrind for profiling Open

DoubangoTelecom/compv#30 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Use dr memory for memory checks (works on Windows unlike valgrind) Open

DoubangoTelecom/compv#31 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
RGBA->I420 C++ version doesn't work Open

DoubangoTelecom/compv#33 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
CompVImage::wrap is very slooow Open

DoubangoTelecom/compv#34 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
replace all cmovs with setcc when possible. The later is supported on all i386 Open

DoubangoTelecom/compv#36 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Compute function pointers onces and update when CPU flags is update Open

DoubangoTelecom/compv#37 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Cache alignment issue on all SIMD code Open

DoubangoTelecom/compv#39 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
cache optimisations and many other stuffs (e.g cupid) must be tested on AMD CPUs Open

DoubangoTelecom/compv#41 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Add unit tests with resolution change Open

DoubangoTelecom/compv#43 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
ImageConv, add x64 versions Open

DoubangoTelecom/compv#48 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
RGBA->I420 with odd width doesn't work or YUV player is buggy Open

DoubangoTelecom/compv#49 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
do not use -march=native on xcode Open

DoubangoTelecom/compv#52 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
getThreadIdxForNextToCurrentCore not correct, must use getThreadIdxCurrent() instead of getCoreId() Open

DoubangoTelecom/compv#53 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Win64 calling convention: stack must be aligned on 16bytes *after* params allocation -> SystemV redzone Open

DoubangoTelecom/compv#54 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
adds support for Short Vector Math Library (SVML) Functions Open

DoubangoTelecom/compv#58 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Add support for Intel® Integrated Performance Primitives (Intel® IPP) Open

DoubangoTelecom/compv#59 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
convlt1_verthz: VS2013 intrin faster than our ASM (not the case for Intel C++) Open

DoubangoTelecom/compv#60 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Promote float to compv_float32_t when sizeof(float) != 4 Open

DoubangoTelecom/compv#61 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
add support for fxp brief decription Open

DoubangoTelecom/compv#63 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Disable x86 ASM when X64 version is available Open

DoubangoTelecom/compv#64 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Add list of customers on doubango.org Open

DoubangoTelecom/compv#65 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Decreasing CPU usage / Speedup Open

DoubangoTelecom/compv#66 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
When testing mode, memZero after malloc() to make sure to have same MD5 result Open

DoubangoTelecom/compv#67 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Samples Open

DoubangoTelecom/compv#68 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
FAST detector, pushing interest points: optimization issue Open

DoubangoTelecom/compv#69 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Rectangular matrixes, optimize using MCOP Open

DoubangoTelecom/compv#71 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026
Some AVX2 functions should be AVX1 Open

DoubangoTelecom/compv#72 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

DoubangoTelecom/compv

Get new issues in your inbox