Training perception systems for self-driving cars requires substantial
a...
Prior work in 3D object detection evaluates models using offline metrics...
The autonomous driving community has witnessed a rapid growth in approac...
The release of nuPlan marks a new era in vehicle motion planning researc...
End-to-end driving systems have recently made rapid progress, in particu...
In this paper, we propose a novel method for joint recovery of camera po...
While progress in 2D generative models of human appearance has been rapi...
Neural radiance fields enable state-of-the-art photorealistic view synth...
Neural implicit representations have recently become popular in simultan...
We present Factor Fields, a novel framework for modeling and representin...
Text-to-image synthesis has recently seen significant progress thanks to...
We address the task of open-world class-agnostic object detection, i.e.,...
Neural fields have revolutionized the area of 3D reconstruction and nove...
Visually exploring in a real-world 4D spatiotemporal space freely in VR ...
Planning an optimal route in a complex environment requires efficient
re...
Combining human body models with differentiable rendering has recently
e...
State-of-the-art 3D-aware generative models rely on coordinate-based MLP...
In recent years, neural implicit surface reconstruction methods have bec...
How should we integrate representations from complementary sensors for
a...
Simulators offer the possibility of safe, low-cost development of
self-d...
Large-scale training data with high-quality annotations is critical for
...
We present TensoRF, a novel approach to model and reconstruct radiance
f...
We present a novel method to learn Personalized Implicit Neural Avatars
...
Computer graphics has experienced a recent surge of data-centric approac...
To make 3D human avatars widely available, we must be able to generate a...
Neural Radiance Fields (NeRF) have emerged as a powerful representation ...
The key objective of Generative Adversarial Networks (GANs) is to genera...
Generative Adversarial Networks (GANs) produce high-quality images but a...
The ability to synthesize realistic and diverse indoor furniture layouts...
For the last few decades, several major subfields of artificial intellig...
Efficient reasoning about the semantic, spatial, and temporal structure ...
In order to handle the challenges of autonomous driving, deep learning h...
In this paper, we aim to create generalizable and controllable neural si...
In recent years, neural implicit representations gained popularity in 3D...
Neural implicit 3D representations have emerged as a powerful paradigm f...
How should representations from complementary sensors be integrated for
...
Registering point clouds of dressed humans to parametric human models is...
Neural implicit surface representations have emerged as a promising para...
Despite stereo matching accuracy has greatly improved by deep learning i...
Tremendous progress in deep generative models has led to photorealistic ...
NeRF synthesizes novel views of a scene with unprecedented quality by fi...
Impressive progress in 3D shape extraction led to representations that c...
In this paper, we tackle video panoptic segmentation, a task that requir...
Neural networks are prone to learning shortcuts – they often model simpl...
Deep generative models allow for photorealistic image synthesis at high
...
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate.
...
Many object pose estimation algorithms rely on the analysis-by-synthesis...
While 2D generative adversarial networks have enabled high-resolution im...
Neural rendering techniques promise efficient photo-realistic image synt...
Perceiving the world in terms of objects is a crucial prerequisite for
r...