Kaustav Kundu

Learn More
The goal of this paper is to generate high-quality 3D object proposals in the context of autonomous driving. Our method exploits stereo imagery to place proposals in the form of 3D bounding boxes. We formulate the problem as minimizing an energy function encoding object size priors, ground plane as well as several depth informed features that reason about(More)
The goal of this paper is to perform 3D object detection from a single monocular image in the domain of autonomous driving. Our method first aims to generate a set of candidate class-specific object proposals, which are then run through a standard CNN pipeline to obtain high-quality object detections. The focus of this paper is on proposal generation. In(More)
We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of traffic participants which move rigidly in 3D. We propose to estimate the traffic participants using instance-level(More)
The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth(More)
The goal of this paper is to enable a 3D “virtual-tour” of an apartment given a small set of monocular images of different rooms, as well as a 2D floor plan. We frame the problem as inference in a Markov Random Field which reasons about the layout of each room and its relative pose (3D rotation and translation) within the full apartment. This(More)
We propose an approach for semi-automatic annotation of object instances. While most current methods treat object segmentation as a pixel-labeling problem, we here cast it as a polygon prediction task, mimicking how most current datasets have been annotated. In particular, our approach takes as input an image crop and sequentially produces vertices of the(More)
Hij = K ·Rij ·K−1. Here Rij denotes a column-wise permutation of R, shuffling the columns i and j to be column 1 and 2. 1.1. Computing y4 from y1, y2 and y3 Let a be a known aspect ratio defined as w/h, where h is the height and w the width of the front wall in the physical world (we know these dimensions from the rental site). Then, given two corner points(More)
Browsers of personal digital photographs all essentially follow the slide show paradigm, sequencing through the photos in the order they are taken. A more engaging way to browse personal photographs, especially of a large space like a popular monument, should involve the geometric context of the space. In this paper, we present a <i>geometry directed photo(More)
Recently Wireless Sensor Networks are used in applications that are "close to human" (healthcare, context sensing etc.) as well as "close to the environment" (weather sensing, seismic activity sensing, disaster warning etc.). Many of these applications are prone to security threats. Due to lightweight processors, limited battery etc. sophisticated(More)
  • 1