53 citations · 227 across the 37 of their papers we have counts for
9 papers · 1 filter
NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
Zuria Bauer, Zuoyue Li, Sergio Orts-Escolano +3
Building upon the recent progress in novel view synthesis, we propose its application to improve monocular depth estimation. In particular, we propose a novel training method split…
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
Zihan Zhu, Songyou Peng, Viktor Larsson +5
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Neverthele…
Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos
Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari +1
We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. To this end, we model the blurred appearance of a…
BoxeR: Box-Attention for 2D and 3D Transformers
Duy-Kien Nguyen, Jihong Ju, Olaf Booij +2
In this paper, we propose a simple attention mechanism, we call box-attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves…
Non-local Recurrent Regularization Networks for Multi-view Stereo
Qingshan Xu, Martin R. Oswald, Wenbing Tao +2
In deep multi-view stereo networks, cost regularization is crucial to achieve accurate depth estimation. Since 3D cost volume filtering is usually memory-consuming, recurrent 2D co…
RealisticHands: A Hybrid Model for 3D Hand Reconstruction
Michael Seeber, Roi Poranne, Marc Polleyfeys +1
Estimating 3D hand meshes from RGB images robustly is a highly desirable task, made challenging due to the numerous degrees of freedom, and issues such as self similarity and occlu…
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes
Davide Menini, Suryansh Kumar, Martin R. Oswald +3
This paper presents a real-time online vision framework to jointly recover an indoor scene's 3D structure and semantic label. Given noisy depth maps, a camera trajectory, and 2D se…
Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects
Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari +1
We address the novel task of jointly reconstructing the 3D shape, texture, and motion of an object from a single motion-blurred image. While previous approaches address the deblurr…
SOLD2: Self-supervised Occlusion-aware Line Description and Detection
Rémi Pautrat, Juan-Ting Lin, Viktor Larsson +2
Compared to feature point detection and description, detecting and matching line segments offer additional challenges. Yet, line features represent a promising complement to points…