Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations · HackerPapers discussions

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations — mentioned by etaioinshrdlu

Tue, 10 Dec 2019 19:24:11 GMT

Being able to measure our successes and failures is the first step towards better algorithms :) This is always exciting. I don't think anyone thought that vanilla CNN architectures were all that would ever be needed. This paper which received an honorable mention this year from NeurIPS conference first attempts to convert the image to a 3d scene before detecting objects. https://arxiv.org/pdf/1906.01618.pdf

Paper and discussion history. A mention is not an endorsement.

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations — mentioned by nmca

Fri, 11 Oct 2019 07:35:40 GMT

At some point you stop caring about being able to import a set of imagnet pretrained weights and start caring about extreme flexibility. Think about implement ting, say "Scene Representation Networks" https://arxiv.org/abs/1906.01618 in each of the three frameworks. Tf is a pig, pytorch is slow, and Jax is going to crush the problem. The lack of say, keras.applications is a shame, but it won't last, and if you have a GPU or 8 the power of optimized (p/v)map definitely makes up for it.

Paper and discussion history. A mention is not an endorsement.