activity
20232026
collaborators

8 papers

cs.CV2026

Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Pose

Zhilin Guo, Boqiao Zhang, Oszkár Urbán +8

Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientations are biased, mounting var…

cs.CV2026

One Sensor, Whole Body - 3D Body Pose from a Single Consumer Earbud IMU

Zhilin Guo, Boqiao Zhang, Oszkár Urbán +8

Consumer earbuds already stream inertial motion data from the head, one of the most widely worn sensor locations on the body. We ask how much of the 3D body pose a single such head…

cs.CV2026

GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes

Josef Bengtson, Yaroslava Lochman, Fredrik Kahl

Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization. Most existing works foc…

cs.CV2026

Matryoshka Gaussian Splatting

Zhilin Guo, Boqiao Zhang, Hakan Aktas +11

The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existi…

cs.CV2025

3D-Consistent Multi-View Editing by Correspondence Guidance

Josef Bengtson, David Nilsson, Dong In Lee +2

Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently often produce geometrically and photomet…

cs.CV2025

Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models

Josef Bengtson, David Nilsson, Fredrik Kahl

Diffusion models for single image novel view synthesis (NVS) can generate highly realistic and plausible images, but they are limited in the geometric consistency to the given rela…

cs.CV2023

FlowIBR: Leveraging Pre-Training for Efficient Neural Image-Based Rendering of Dynamic Scenes

Marcel Büsching, Josef Bengtson, David Nilsson +1

We introduce FlowIBR, a novel approach for efficient monocular novel view synthesis of dynamic scenes. Existing techniques already show impressive rendering quality but tend to foc…

cs.CV2023

Adjustable Visual Appearance for Generalizable Novel View Synthesis

Josef Bengtson, David Nilsson, Che-Tsung Lin +2

We present a generalizable novel view synthesis method which enables modifying the visual appearance of an observed scene so rendered views match a target weather or lighting condi…