Martin R. Oswald

Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding CVPR 2026 Edge-Centric Relational Reasoning for 3D Scene Graph Prediction AAAI 2026 From Rays to Projections: Better Inputs for Feed-Forward View Synthesis CVPR 2026 Gaussian Mapping for Evolving Scenes CVPR 2026 Unblur-SLAM: Dense Neural SLAM for Blurry Inputs CVPR 2026 3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation CVPR 2025 ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction WACV 2025 An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels ICLR 2025 Auto-Vocabulary Semantic Segmentation ICCV 2025 MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM CVPR 2025 ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos CVPR 2025 SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining ICCV 2025 Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping ICCV 2025 ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration ICCV 2025 TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning ICCV 2025 Union-over-Intersections: Object Detection beyond Winner-Takes-All ICLR 2025 Loopy-SLAM: Dense Neural SLAM with Loop Closures CVPR 2024 R-MAE: Regions Meet Masked Autoencoders ICLR 2024 Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion CVPR 2024 T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning ECCV 2024 WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation ECCV 2024 DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients CVPR 2023 Detecting Objects with Context-Likelihood Graphs and Graph Refinement ICCV 2023 Human from Blur: Human Pose Tracking from Blurry Images ICCV 2023 Point-SLAM: Dense Neural Point Cloud-based SLAM ICCV 2023 The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes NeurIPS 2023 Tracking by 3D Model Estimation of Unknown Objects in Videos ICCV 2023 BoxeR: Box-Attention for 2D and 3D Transformers CVPR 2022 CompNVS: Novel View Synthesis with Scene Completion ECCV 2022 Learning Online Multi-sensor Depth Fusion ECCV 2022 Motion-From-Blur: 3D Shape and Motion Estimation of Motion-Blurred Objects in Videos CVPR 2022 NICE-SLAM: Neural Implicit Scalable Encoding for SLAM CVPR 2022 DeepSurfels: Learning Online Appearance Fusion CVPR 2021 DeFMO: Deblurring and Shape Recovery of Fast Moving Objects CVPR 2021 FMODetect: Robust Detection of Fast Moving Objects ICCV 2021 NeuralFusion: Online Depth Fusion in Latent Space CVPR 2021 Sat2Vid: Street-View Panoramic Video Synthesis From a Single Satellite Image ICCV 2021 Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects NeurIPS 2021 SOLD2: Self-Supervised Occlusion-Aware Line Description and Detection CVPR 2021 Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas CVPR 2020 Online Invariance Selection for Local Feature Descriptors ECCV 2020 RoutedFusion: Learning Real-Time Depth Map Fusion CVPR 2020 3D Instance Segmentation via Multi-Task Metric Learning ICCV 2019 Consensus Maximization for Semantic Region Correspondences CVPR 2018 Learning Priors for Semantic 3D Reconstruction ECCV 2018 Consensus Maximization With Linear Matrix Inequality Constraints CVPR 2017 Fast 3D Reconstruction of Faces With Glasses CVPR 2017 Semantically Informed Multiview Surface Refinement ICCV 2017 Entropy Minimization for Convex Relaxation Approaches ICCV 2015