[Theory] NOW: 6/16 Thesis Defense: Igor Vasiljevic, TTIC

Mary Marre mmarre at ttic.edu
Thu Jun 16 15:01:47 CDT 2022


*Thesis Defense: Igor Vasiljevic, TTIC*

*When:  *     Thursday, June 16th at *3:00 - 5:00 pm CT*


*Where:       *Talk will be given *live, in-person* at

                   TTIC, 6045 S. Kenwood Avenue

                   5th Floor, Room 529



*Virtually: *  *via zoom (join here
<https://uchicagogroup.zoom.us/j/97343266685?pwd=elB4RnJUQ1p1b0lWOFR2anBzN2ZXUT09>)*



*Who: *        Igor Vasiljevic, TTIC


*Thesis Title: *Neural Camera Models

*Abstract: * Modern computer vision has moved beyond the domain of internet
photo collections and into the physical world, guiding camera-equipped
robots and autonomous cars through unstructured environments. To enable
these embodied agents to interact with real-world objects, cameras are
increasingly being used as depth sensors (through depth estimation),
reconstructing the environment for a variety of downstream reasoning tasks.

While impressive strides have been made in depth estimation, significant
challenges remain: (1) ground truth depth labels are difficult and
expensive to collect at scale, (2) camera information is typically assumed
to be known, but is often unreliable and (3) restrictive (typically
pinhole) camera assumptions are common, even though a great variety of
camera types and lenses are used in practice. In this thesis, we focus on
relaxing these assumptions, and describe contributions toward the ultimate
goal of turning cameras into truly generic depth sensors.


*Thesis Advisor:*
*Greg Shakhnarovich* <greg at ttic.edu>

Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Chicago, IL  60637*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Thu, Jun 16, 2022 at 2:25 PM Mary Marre <mmarre at ttic.edu> wrote:

> *Thesis Defense: Igor Vasiljevic, TTIC*
>
> *When:  *     Thursday, June 16th at *3:00 - 5:00 pm CT*
>
>
> *Where:       *Talk will be given *live, in-person* at
>
>                    TTIC, 6045 S. Kenwood Avenue
>
>                    5th Floor, Room 529
>
>
>
> *Virtually: *  *via zoom (join here
> <https://uchicagogroup.zoom.us/j/97343266685?pwd=elB4RnJUQ1p1b0lWOFR2anBzN2ZXUT09>)*
>
>
>
> *Who: *        Igor Vasiljevic, TTIC
>
>
> *Thesis Title: *Neural Camera Models
>
> *Abstract: * Modern computer vision has moved beyond the domain of
> internet photo collections and into the physical world, guiding
> camera-equipped robots and autonomous cars through unstructured
> environments. To enable these embodied agents to interact with real-world
> objects, cameras are increasingly being used as depth sensors (through
> depth estimation), reconstructing the environment for a variety of
> downstream reasoning tasks.
>
> While impressive strides have been made in depth estimation, significant
> challenges remain: (1) ground truth depth labels are difficult and
> expensive to collect at scale, (2) camera information is typically assumed
> to be known, but is often unreliable and (3) restrictive (typically
> pinhole) camera assumptions are common, even though a great variety of
> camera types and lenses are used in practice. In this thesis, we focus on
> relaxing these assumptions, and describe contributions toward the ultimate
> goal of turning cameras into truly generic depth sensors.
>
>
> *Thesis Advisor:*
> *Greg Shakhnarovich* <greg at ttic.edu>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Chicago, IL  60637*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Wed, Jun 15, 2022 at 5:06 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *Thesis Defense: Igor Vasiljevic, TTIC*
>>
>> *When:  *     Thursday, June 16th at *3:00 - 5:00 pm CT*
>>
>>
>> *Where:       *Talk will be given *live, in-person* at
>>
>>                    TTIC, 6045 S. Kenwood Avenue
>>
>>                    5th Floor, Room 529
>>
>>
>>
>> *Virtually: *  *via zoom (join here
>> <https://uchicagogroup.zoom.us/j/97343266685?pwd=elB4RnJUQ1p1b0lWOFR2anBzN2ZXUT09>)*
>>
>>
>>
>> *Who: *        Igor Vasiljevic, TTIC
>>
>>
>> *Thesis Title: *Neural Camera Models
>>
>> *Abstract: * Modern computer vision has moved beyond the domain of
>> internet photo collections and into the physical world, guiding
>> camera-equipped robots and autonomous cars through unstructured
>> environments. To enable these embodied agents to interact with real-world
>> objects, cameras are increasingly being used as depth sensors (through
>> depth estimation), reconstructing the environment for a variety of
>> downstream reasoning tasks.
>>
>> While impressive strides have been made in depth estimation, significant
>> challenges remain: (1) ground truth depth labels are difficult and
>> expensive to collect at scale, (2) camera information is typically assumed
>> to be known, but is often unreliable and (3) restrictive (typically
>> pinhole) camera assumptions are common, even though a great variety of
>> camera types and lenses are used in practice. In this thesis, we focus on
>> relaxing these assumptions, and describe contributions toward the ultimate
>> goal of turning cameras into truly generic depth sensors.
>>
>>
>> *Thesis Advisor:*
>> *Greg Shakhnarovich* <greg at ttic.edu>
>>
>>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Chicago, IL  60637*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>>
>> On Tue, Jun 14, 2022 at 10:30 AM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *Thesis Defense: Igor Vasiljevic, TTIC*
>>>
>>> *When:  *     Thursday, June 16th at *3:00 - 5:00 pm CT*
>>>
>>>
>>> *Where:       *Talk will be given *live, in-person* at
>>>
>>>                    TTIC, 6045 S. Kenwood Avenue
>>>
>>>                    5th Floor, Room 529
>>>
>>>
>>>
>>> *Virtually: *  *via zoom (join here
>>> <https://uchicagogroup.zoom.us/j/97343266685?pwd=elB4RnJUQ1p1b0lWOFR2anBzN2ZXUT09>)*
>>>
>>>
>>>
>>> *Who: *        Igor Vasiljevic, TTIC
>>>
>>>
>>> *Thesis Title: *Neural Camera Models
>>>
>>> *Abstract: * Modern computer vision has moved beyond the domain of
>>> internet photo collections and into the physical world, guiding
>>> camera-equipped robots and autonomous cars through unstructured
>>> environments. To enable these embodied agents to interact with real-world
>>> objects, cameras are increasingly being used as depth sensors (through
>>> depth estimation), reconstructing the environment for a variety of
>>> downstream reasoning tasks.
>>>
>>> While impressive strides have been made in depth estimation, significant
>>> challenges remain: (1) ground truth depth labels are difficult and
>>> expensive to collect at scale, (2) camera information is typically assumed
>>> to be known, but is often unreliable and (3) restrictive (typically
>>> pinhole) camera assumptions are common, even though a great variety of
>>> camera types and lenses are used in practice. In this thesis, we focus
>>> on relaxing these assumptions, and describe contributions toward the
>>> ultimate goal of turning cameras into truly generic depth sensors.
>>>
>>>
>>> *Thesis Advisor:*
>>> *Greg Shakhnarovich* <greg at ttic.edu>
>>>
>>>
>>> Mary C. Marre
>>> Faculty Administrative Support
>>> *Toyota Technological Institute*
>>> *6045 S. Kenwood Avenue*
>>> *Chicago, IL  60637*
>>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>>
>>>
>>> On Tue, Jun 7, 2022 at 11:22 AM Mary Marre <mmarre at ttic.edu> wrote:
>>>
>>>> *Thesis Defense: Igor Vasiljevic, TTIC*
>>>>
>>>> *When:  *     Thursday, June 16th at *3:00 - 5:00 pm CT*
>>>>
>>>>
>>>> *Where:       *Talk will be given *live, in-person* at
>>>>
>>>>                    TTIC, 6045 S. Kenwood Avenue
>>>>
>>>>                    5th Floor, Room 529
>>>>
>>>>
>>>>
>>>> *Virtually: *  *via zoom (join here
>>>> <https://uchicagogroup.zoom.us/j/97343266685?pwd=elB4RnJUQ1p1b0lWOFR2anBzN2ZXUT09>)*
>>>>
>>>>
>>>>
>>>> *Who: *        Igor Vasiljevic, TTIC
>>>>
>>>>
>>>> *Thesis Title: *Neural Camera Models
>>>>
>>>> *Abstract: * Modern computer vision has moved beyond the domain of
>>>> internet photo collections and into the physical world, guiding
>>>> camera-equipped robots and autonomous cars through unstructured
>>>> environments. To enable these embodied agents to interact with real-world
>>>> objects, cameras are increasingly being used as depth sensors (through
>>>> depth estimation), reconstructing the environment for a variety of
>>>> downstream reasoning tasks.
>>>>
>>>> While impressive strides have been made in depth estimation,
>>>> significant challenges remain: (1) ground truth depth labels are difficult
>>>> and expensive to collect at scale, (2) camera information is typically
>>>> assumed to be known, but is often unreliable and (3) restrictive (typically
>>>> pinhole) camera assumptions are common, even though a great variety of
>>>> camera types and lenses are used in practice. In this thesis, we focus on
>>>> relaxing these assumptions, and describe contributions toward the ultimate
>>>> goal of turning cameras into truly generic depth sensors.
>>>>
>>>>
>>>> *Thesis Advisor:*
>>>> *Greg Shakhnarovich* <greg at ttic.edu>
>>>>
>>>>
>>>>
>>>> Mary C. Marre
>>>> Faculty Administrative Support
>>>> *Toyota Technological Institute*
>>>> *6045 S. Kenwood Avenue*
>>>> *Chicago, IL  60637*
>>>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>>>
>>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20220616/1dea2793/attachment-0001.html>


More information about the Theory mailing list