Christian Rupprecht

21

Papers

763

Total Citations

Papers (21)

Splatter Image: Ultra-Fast Single-View 3D Reconstruction

CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos

FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

Learning the 3D Fauna of the Web

Dataset Enhancement with Instance-Level Augmentations

Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks

AnimalClue: Recognizing Animals by their Traces

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos

IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation

CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts

SynCity: Training-Free Generation of 3D Cities

DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness

Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics

VGGT: Visual Geometry Grounded Transformer

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Scene-Centric Unsupervised Panoptic Segmentation

Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels