[IPOL discuss] optic flow algorithms in ipol

[Nicolas Limare]

> The paper of Horn & Schunck proposes an implementation in full detail.
> Any two correct implementations of this paper will produce exactly
> the same results
> [...]
> Indeed, all the implementations of this algorithm that I tried,
> including my own, produce vastly different results.

Isn't there a contradiction here? Or does it mean that all the
implementations you have tried were not correct implementations?

-- 
Nicolas LIMARE - CMLA - ENS Cachan    http://www.cmla.ens-cachan.fr/~limare/
IPOL - image processing on line                          http://www.ipol.im/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 198 bytes
Desc: Digital signature
URL: <http://tools.ipol.im/mailman/archive/discuss/attachments/20110927/25f86fe7/attachment.pgp>