William Ljungbergh

phd student @ zenseact researching e2e driving for autonomous vehicles

[William Ljungbergh @wljungbergh]

@BenMildenhall Would be cool to see how it works in traffic

[MrNeRF @janusch_patas]

SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving

Contributions:
• We propose the first method for efficient lidar rendering using 3D Gaussians, introducing custom CUDA-accelerated algorithms for rasterizing sparse point clouds in spherical coordinates.

• We introduce the first 3DGS method capable of rendering both camera and lidar from a unified representation, enabling accelerated scaling of novel view synthesis for automotive applications.

• We present effective techniques for realistic sensor modeling using 3D Gaussians, enabling accurate handling of rolling shutter, lidar intensity, ray dropping, and variations in sensor appearance.

• Through extensive evaluation on three popular automotive datasets, we demonstrate state-of-the-art results across all benchmarks, validating our method’s effectiveness and generalizability.

[Andrei Bursuc @abursuc]

A few personal picks from poster session #6 (Thu PM) #ECCV2024 1/

[William Ljungbergh @wljungbergh]

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

We leverage neural rendering to create safety-critical AD scenarios and show that SOTA AD models fail drastically.

page: https://t.co/dwXpQHXS8i
code: https://t.co/0PnpmQznoq
hf: https://t.co/2q9Uy73aRv

[Georg Hess @GeorgHess3]

NeuRAD code is live! Check out for our nerfstudio-integrated SOTA neural rendering method for autonomous driving

https://t.co/zFjSQfHH4Y

[Computer Vision Laboratory (CVL), Linköping @CvlIsy]

Check our latest pre-print: "NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving"!
Leveraging neural rendering, we replicate real-world driving data to simulate safety-critical scenarios & evaluate autonomous systems end-to-end.
https://t.co/n8JagdlFCQ

[Zhenjun Zhao @zhenjun_zhao]

NeuRAD: Neural Rendering for Autonomous Driving

Adam Tonderski, Carl Lindström, Georg Hess, William Ljungbergh, Lennart Svensson, Christoffer Petersson

tl;dr: handle lidar and camera data in 360◦ and decompose the world into static and dynamic elements

https://t.co/OOs30ibjCN

[Tomorrowland @tomorrowland]

Forever in our hearts

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 1-2 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 2-1 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 1-1 #hundralappen

[William Ljungbergh @wljungbergh]

@Johan95hansson @Unibet_Sverige @eliasstuchly

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 1-1 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 2-0 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 1-1 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 1-3 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 0-0 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 3-0 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 3-3 #hundralappen

[William Ljungbergh @wljungbergh]

@Unibet_Sverige 2-0 #hundralappen