This interaction field guides the sampling of an object-conditioned human motion diffusion model, so as to encourage plausible contacts and affordance semantics.
Obtaining 3D meshes from neural radiance fields still remains an open challenge since NeRFs are optimized for view synthesis, not enforcing an accurate underlying geometry on the radiance field.
We address efficient and structure-aware 3D scene representation from images.
We take a step towards addressing this shortcoming by introducing a model that encodes the input image into a disentangled object representation that contains a code for object shape, a code for object appearance, and an estimated camera pose from which the object image is captured.
Our model builds a panoptic radiance field representation of any scene from just color images.
1 code implementation • • Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti, Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras.
Ranked #8 on LIDAR Semantic Segmentation on nuScenes
Features from multiple per view predictions are finally fused on 3D mesh vertices to predict mesh semantic segmentation labels.
Ranked #11 on Semantic Segmentation on ScanNet
We use a U-Net style 3D sparse convolution network to extract features for each frame's LiDAR point-cloud.
We present a simple and flexible object detection framework optimized for autonomous driving.
In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes.
In this work, we present a novel approach for color texture generation using a conditional adversarial loss obtained from weakly-supervised views.
Our method produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving.
Ranked #3 on Vehicle Pose Estimation on KITTI Cars Hard (using extra training data)