SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans - YouTube

SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans - YouTube

Paper: https://arxiv.org/pdf/1912.00036 Project: https://angeladai.github.io/dai2019sgnn.html We present a novel approach that converts partial and noisy RGB...

1 mentions: @MattNiessner
Date: 2019/12/03 18:51

Referring Tweets

@MattNiessner SG-NN: Sparse Generative Neural Networks for fully self-supervised Scene Completion. t.co/Veraj9Q2AZ - No need for ground truth geometry - Only need real-world (partial) 3D scans More complete predictions than any GT training sample by self-supervision :) @angelaqdai t.co/TvclqHIbpk

Related Entries

Read more TUM Visual Computing: Prof. Matthias Nießner
0 users, 1 mentions 2020/01/15 03:50
Read more I2DL
0 users, 1 mentions 2020/03/13 02:20
Read more GitHub - reviewingNLP/ACL2020T3material: Contains all teaching material used in ACL 2020 Tutorial "R...
0 users, 1 mentions 2020/07/08 17:21
Read more The State and Fate of Linguistic Diversity and Inclusion in the NLP World - ACL Anthology
0 users, 3 mentions 2020/07/11 15:51
Read more [2006.13707] Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functionso...
0 users, 1 mentions 2020/07/19 00:52