With #COVID19 many research internship will be cancelled... so why not participate in a Google Summer of Code #GSoC instead, be exposed to cutting edge research, and make some extra $$?
#TensorFlowGraphics have several projects posted here: https://t.co/bvEajxyGq2
If you are at #NeurIPS2019 , don't miss our paper on sparse multi-view (1 or more) object reconstruction. **Wed Dec 11th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #96** Joint work with: @davrempe@JPCValentin@_sofien_ Leo Guibas. @NeurIPSConf
ViewAL: active learning with viewpoint entropy! https://t.co/HrVIXGESIn
Only 7% training data, achieves 95% network performance!
Simple idea:
If network makes inconsistent predictions across views, we need more training data for these cases :)
#DeepLearning-now-needs-less-data
@zkajdan I unfortunately did not plan what you described for the next release. I would nevertheless be happy to have the discussion with you if you would be interested to contribute.
Best.
@drsrinathsridha The demo scene is quite fun.
Some ML people should generate an hours long video generated from a recurrent net to show them what we can do :P
Our Deep View Synthesis CVPR 2019 paper is now online https://t.co/PYGENZA3ma , with examples of Light Field Video https://t.co/4X8vkAqJgm and an interactive multi-plane image (MPI) viewer to try the view interpolation technique for yourself https://t.co/0aplX6MinP
How can we estimate the 6D pose and size of novel object instances that we have never seen before? Come find how we do category-level 6D pose and size estimation at our #CVPR2019 oral today (~15:00, Promenade Ballroom, Poster #181). Code/data available! https://t.co/XtH18ftgdg