In this paper, we systematically study the impact of various self-supervised learning proxy tasks on different architectures and threat models for 3D point clouds with adversarial training.
To this end, we first learn joint embeddings of freeform text descriptions and colored 3D shapes.
Coarse voxel predictions from a 3D Fully Convolutional NN are transferred back to the raw 3D points via trilinear interpolation.
Ranked #13 on Semantic Segmentation on Semantic3D
Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks.
DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting for the multi-modal nature of the future prediction (i. e., given the same context, future may vary), 2) foreseeing the potential future outcomes and make a strategic prediction based on that, and 3) reasoning not only from the past motion history, but also from the scene context as well as the interactions among the agents.
Ranked #1 on Trajectory Prediction on PAID
In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image.
We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations.
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2).
Ranked #4 on 3D Reconstruction on Data3D−R2N2