Goto

Collaborating Authors

 Country



bbc9d480a8257889d2af88983e8b126a-Paper-Conference.pdf

Neural Information Processing Systems

While existing automatic differentiation (AD) frameworks allow flexibly composing model architectures, theydonotprovide thesame flexibility forcomposing learning algorithms--everything has to be implemented in terms of backpropagation.



From Visual Question Answering to multimodal learning: an interview with Aishwarya Agrawal

AIHub

You were awarded an Honourable Mention for the 2019 AAAI / ACM SIGAI Doctoral Dissertation Award. What was the topic of your dissertation research, and what were the main contributions or findings? My PhD dissertation was on the topic of Visual Question Answering, called VQA. We proposed the task of open-ended and free-form VQA - a new way to benchmark computer vision models by asking them questions about images. We curated a large-scale dataset for researchers to train and test their models on this task.



NeuS: LearningNeuralImplicitSurfaces byVolumeRenderingforMulti-viewReconstruction-SupplementaryMaterial-ADerivationforComputingOpacityฮฑi

Neural Information Processing Systems

Next consider the case where[ti,ti+1] lies in a range[t`,tr] over which the camera ray is exiting the surface, i.e. the signed distance function is increasing onp(t) over [t`,tr]. Then we have ( f(p(t)) v) < 0 in [ti,ti+1]. Then, according to Eqn. 1, we haveฯ(t) = 0. Therefore, by Eqn.12ofthepaper,wehave ฮฑi=1 exp Recall that our S-density fieldฯ†s(f(x)) is defined using the logistic density functionฯ†s(x) = se sx/(1+e sx)2, which is the derivative of the Sigmoid functionฮฆs(x) = (1+e sx) 1, i.e. ฯ†s(x)=ฮฆ0s(x). As a first-order approximation of signed distance functionf, suppose that locally the surface is tangentially approximated byasufficiently small planar patch with itsoutwardunitnormal vector denotedas n. Nowsupposep(t)isapoint on the surfaceS,that is, f(p(t)) = 0. Next we will examine the value ofdwdt(t) at t = t . Thesigneddistancefunction f ismodeledbyanMLP that consists of 8hidden layers with hidden size of 256.