Analyzing Deep Learning Representations for Real-Time In-Vehicle LiDAR Perception
Dec 2, 2022
Speakers
Marc Uecker
Speaker · 0 followers
Tobias Fleck
Speaker · 0 followers
Marcel Pflugfelder
Speaker · 0 followers
Marius Zöllner
Speaker · 0 followers
About
LiDAR sensors are an integral part of modern autonomous vehicles as they provide an accurate, high-resolution 3D representation of the vehicle's surroundings. However, it is computationally difficult to make use of the ever-increasing amounts of data from multiple high-resolution LiDAR sensors. As frame-rates, point cloud sizes and sensor resolutions increase, real-time processing of these point clouds must still extract semantics from this increasingly precise picture of the vehicle's environment. One deciding factor of the run-time performance and accuracy of deep neural networks operating on these point clouds is the underlying data representation and the way it is computed. In this work, we examine the relationship between the computational representations used in neural networks and their performance characteristics. To this end, we propose a novel computational taxonomy of LiDAR point cloud representations used in modern deep neural networks for 3D point cloud processing. Using this taxonomy, we perform a structured analysis of different families of approaches. Thereby, we uncover common advantages and limitations in terms of computational efficiency, memory requirements, and representational capacity as measured by semantic segmentation performance. Finally, we provide some insights and guidance for future developments in neural point cloud processing methods.LiDAR sensors are an integral part of modern autonomous vehicles as they provide an accurate, high-resolution 3D representation of the vehicle's surroundings. However, it is computationally difficult to make use of the ever-increasing amounts of data from multiple high-resolution LiDAR sensors. As frame-rates, point cloud sizes and sensor resolutions increase, real-time processing of these point clouds must still extract semantics from this increasingly precise picture of the vehicle's environme…
Organizer
NeurIPS 2022
Account · 961 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Approximation with CNNs in Sobolev Space: with Applications to Classification
Watch later
Guohao Shen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Beyond L1: Faster and Better Sparse Models with skglm
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning from uncertain concepts via test time interventions
Watch later
Ivaxi Sheth, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Closing
Watch later
Rida Qadri, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
De Novo Protein Design
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
AntiFaceGAN: Animatable 3D-Aware Face Image Generation for Realistic Video Avatars
Watch later
Yue Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%