[snip]
> This difference between html and images (or postscript) is
> fundamental and is one of the reasons I like html so much.
Me too, although in my case 'so much' isn't all that much anymore...
> Now consider VRML. VRML specifies the exact appearance of
> a 3D scene (within hardware limitations). This is much like
> an image -- not much like html.
True.
> Question: can VRML be modified to specify the sturcture
> of a world? I.e., can we express the
> logical groupings of information in a 3D environment without
> giving x,y,z, color, normal, etc. type information and leave
> these details to the browser?
More important question: should it?
I think the answer is no. The logical and 'physical' specification of
scenes should be kept in separate formats, because:
1. A logically specified scene cannot support the sharing of space in
any obvious manner
With a unified language, you'd have to have concepts of 'clean' VRML that
specifies spatial relationships exactly and 'dirty' ones such that
different browsers or different sessions of the same browser could get
crossed up sharing the space. Among other things, it would be bad to
make sure logical space specification gets labelled 'dirty'. With
separate languages, VRML would ALWAYS be 'clean' in that manner; the
Logical Scene Description Language, on the other hand, would be turned
into VRML by the simulation server.
2. Embedding this into VRML would encourage a specific way of doing
this too much.
Let's face it--the logical structures of rooms and landscapes are much
less understood than those of text, and even in the textual domain HTML
as a standard is collapsing under the burden of conflicting demands
because it's trying to be everything to everyone regardless of their
theory of how text should be marked up. Anything anyone designs for
logical scene specification the first time around will be seen as much
more inadequate to its purpose than HTML 1.0 (anything less than a good
interior decorator would), and it'd be horrible if everyone ended up
feeling tied to one of its descendants because it happens to be
embeddable in the most popular low-level scene description language.
[big snip]
> Why bother with WWWlogical?
> * For authors, it allows adding things
> to a world without constantly making sure things fit properly.
> * For users it provides (with the browser's help) more control
> over the layout of their information space.
> * For the network, it reduces the number of bytes necessary to
> specify a world since most graphic detail is left to the browser.
These are also good arguments for LSDL.
> Serious problems:
> * I think building a good browser will be hard
No kidding.
> * the hints field could turn into a tangled mess
This would be much alleviated by changing its role from that of a VRML
field to that of an entire scene description langauge.
-- James Deikun (University of Pittsburgh) #include <std_disclaimer.h> Yet another victim of the "meme" meme-virus.