Manually annotating object bounding boxes is central to building computer vision datasets,
and it is very time consuming (annotating ILSVRC [53] took 35s for one high-quality box …

The creation of a digital representation of the Earth and its associated data is a complex and
difficult task. The incredible size of geospatial data and differences between data sets pose …

Rendering high quality digital terrains at interactive rates requires carefully crafted
algorithms and data structures able to balance the competing requirements of realism and …

We recently introduced an efficient multiresolution structure for distributing and rendering
very large point sampled models on consumer graphics platforms [1]. The structure is based …

In this paper we present a novel approach for interactive rendering of large terrain datasets.
Our approach is based on subdividing a terrain into rectangular patches at different …

We present a LOD rendering technique for large, textured terrain, which is well-suited for
recent GPUs. In a preprocess, we tile the domain, and we compute for each tile a discrete …

With the ever increasing resolution of scanned elevation models, geometry throughput on
the GPU is becoming a severe performance limitation in 3D terrain rendering. In this paper …

View-dependent simplification and rendering have been actively researched for interactive
display of large datasets [Hoppe 1997]. These algorithms have many appealing properties …

We describe a compressed multiresolution representation for supporting interactive
rendering of very large planar and spherical terrain surfaces. The technique, called …

Due to the fundamental weaknesses of level-of-detail (LOD) control and rich details in the
Geometry Clipmaps, we propose a multi-resolution terrain rendering algorithm that utilizes …