Andreas Geiger

82

Papers

692

Total Citations

Papers (82)

The Numerics of GANs

NeurIPS 2017arXiv

Generalized Predictive Model for Autonomous Driving

GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

GenFusion: Closing the Loop between Reconstruction and Generation via Videos

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction

Mip-Splatting: Alias-free 3D Gaussian Splatting

3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing

Object Scene Flow for Autonomous Vehicles

Displets: Resolving Stereo Ambiguities Using Object Knowledge

Patches, Planes and Probabilities: A Non-Local Prior for Volumetric 3D Reconstruction

Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

Semantic Multi-View Stereo: Jointly Estimating Objects and Voxels

A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos

OctNet: Learning Deep 3D Representations at High Resolutions

Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

Toroidal Constraints for Two-Point Localization Under High Outlier Ratios

Learning 3D Shape Completion From Laser Scan Data With Weak Supervision

Deep Marching Cubes: Learning Explicit Surface Representations

RayNet: Learning Volumetric 3D Reconstruction With Ray Potentials

Semantic Visual Localization

Occupancy Networks: Learning 3D Reconstruction in Function Space

Taking a Deeper Look at the Inverse Compositional Algorithm

Connecting the Dots: Learning Representations for Active Monocular Depth Estimation

Learning Non-Volumetric Depth Fusion Using Successive Reprojections

MOTS: Multi-Object Tracking and Segmentation

PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds

Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids

On Joint Estimation of Pose, Geometry and svBRDF From a Handheld Scanner

Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image

Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving

Learning Situational Driving

GIRAFFE: Representing Scenes As Compositional Generative Neural Feature Fields

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

SMD-Nets: Stereo Mixture Density Networks

Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural Networks

PINA: Learning a Personalized Implicit Neural Avatar From a Single RGB-D Video Sequence

gDNA: Towards Generative Detailed Neural Avatars

RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs

Exploiting Object Similarity in 3D Reconstruction

FollowMe: Efficient Online Min-Cost Flow Tracking With Bounded Memory and Computation

Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?

Attacking Optical Flow

Texture Fields: Learning Texture Representations in Function Space

Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics

NEAT: Neural Attention Fields for End-to-End Autonomous Driving

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes

DepthSplat: Connecting Gaussian Splatting and Depth

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation

AG3D: Learning to Generate 3D Avatars from 2D Image Collections

Hidden Biases of End-to-End Driving Models

Convolutional Occupancy Networks

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

ARAH: Animatable Volume Rendering of Articulated Human SDFs

TensoRF: Tensorial Radiance Fields

KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients

KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs

UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation

EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis

Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

MuRF: Multi-Baseline Radiance Fields

NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

ATISS: Autoregressive Transformers for Indoor Scene Synthesis

Shape As Points: A Differentiable Poisson Solver

Projected GANs Converge Faster

On the Frequency Bias of Generative Models

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

Which Training Methods for GANs do actually Converge?