Established surgical navigation systems for pedicle screw placement have...
Estimating camera motion in deformable scenes poses a complex and open
r...
We present an uncertainty learning framework for dense neural simultaneo...
Vision-specific concepts such as "region" have played a key role in exte...
Intelligent robots require object-level scene understanding to reason ab...
Most model-free visual object tracking methods formulate the tracking ta...
We propose a dense neural simultaneous localization and mapping (SLAM)
a...
We propose a method to estimate 3D human poses from substantially blurre...
Neural implicit representations have recently become popular in simultan...
The goal of this paper is to detect objects by exploiting their
interrel...
Line segments are ubiquitous in our human-made world and are increasingl...
The generation of triangle meshes from point clouds, i.e. meshing, is a ...
We introduce a scalable framework for novel view synthesis from RGB-D im...
Many hand-held or mixed reality devices are used with a single sensor fo...
Outdoor webcam images are an information-dense yet accessible visualizat...
Building upon the recent progress in novel view synthesis, we propose it...
We propose a method for jointly estimating the 3D motion, 3D shape, and
...
In this paper, we propose a simple attention mechanism, we call
Box-Atte...
In deep multi-view stereo networks, cost regularization is crucial to ac...
Estimating 3D hand meshes from RGB images robustly is a highly desirable...
This paper presents a real-time online vision framework to jointly recov...
We address the novel task of jointly reconstructing the 3D shape, textur...
Compared to feature point detection and description, detecting and match...
Monocular depth reconstruction of complex and dynamic scenes is a highly...
We present DeepSurfels, a novel hybrid scene representation for geometry...
We propose the first learning-based approach for detection and trajector...
We present a novel method for synthesizing both temporally and geometric...
Objects moving at high speed appear significantly blurred when captured ...
We present a novel online depth map fusion approach that learns depth ma...
Representing scenes at the granularity of objects is a prerequisite for ...
Most of the current scene flow methods choose to model scene flow as a p...
We present a novel 3D shape completion method that operates directly on
...
To be invariant, or not to be invariant: that is the question formulated...
This paper presents the perception, mapping, and planning pipeline
imple...
We present a super-resolution method capable of creating a high-resoluti...
The efficient fusion of depth maps is a key part of most state-of-the-ar...
Volumetric depth map fusion based on truncated signed distance functions...
We propose a novel method for instance label segmentation of dense 3D vo...
We present a method to jointly refine the geometry and semantic segmenta...