Related papers: Hypernom: Mapping VR Headset Orientation to S^3
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…
Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to expensive physical data acquisition, transferring robotic manipulation policies from…
Three-dimensional perception from multi-view cameras is a crucial component in autonomous driving systems, which involves multiple tasks like 3D object detection and bird's-eye-view (BEV) semantic segmentation. To improve perception…
We propose SplitNet, a method for decoupling visual perception and policy learning. By incorporating auxiliary tasks and selective learning of portions of the model, we explicitly decompose the learning objectives for visual navigation into…
Autonomously trained agents that are supposed to play video games reasonably well rely either on fast simulation speeds or heavy parallelization across thousands of machines running concurrently. This work explores a third way that is…
DeepMind's recent spectacular success in using deep convolutional neural nets and machine learning to build superhuman level agents --- e.g. for Atari games via deep Q-learning and for the game of Go via Reinforcement Learning --- raises…
Leveraging the integration of visual and proprioceptive cues, research has uncovered various perception thresholds in VR that can be exploited to support haptic feedback for grasping. While previous studies have explored individual…
Taking over arbitrary tasks like humans do with a mobile service robot in open-world settings requires a holistic scene perception for decision-making and high-level control. This paper presents a human-inspired scene perception model to…
The lack of proper class discrimination among the Hyperspectral (HS) data points poses a potential challenge in HS classification. To address this issue, this paper proposes an optimal geometry-aware transformation for enhancing the…
Tissue loss in the hippocampi has been heavily correlated with the progression of Alzheimer's Disease (AD). The shape and structure of the hippocampus are important factors in terms of early AD diagnosis and prognosis by clinicians.…
We introduce NeoWorld, a deep learning framework for generating interactive 3D virtual worlds from a single input image. Inspired by the on-demand worldbuilding concept in the science fiction novel Simulacron-3 (1964), our system constructs…
We present a method for learning multiple scene representations given a small labeled set, by exploiting the relationships between such representations in the form of a multi-task hypergraph. We also show how we can use the hypergraph to…
The goal of object navigation is to reach the expected objects according to visual information in the unseen environments. Previous works usually implement deep models to train an agent to predict actions in real-time. However, in the…
We generalise the hyperplane separation technique (Chatterjee and Velner, 2013) from multi-dimensional mean-payoff to energy games, and achieve an algorithm for solving the latter whose running time is exponential only in the dimension, but…
We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The goal of the game is to locate an unknown object in a rich image scene by asking a sequence of…
Pansharpening aims to fuse a registered high-resolution panchromatic image (PAN) with a low-resolution hyperspectral image (LR-HSI) to generate an enhanced HSI with high spectral and spatial resolution. Existing pansharpening approaches…
Autonomous robot manipulation involves estimating the translation and orientation of the object to be manipulated as a 6-degree-of-freedom (6D) pose. Methods using RGB-D data have shown great success in solving this problem. However, there…
Deep learning for predicting or generating 3D human pose sequences is an active research area. Previous work regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain,…
This workshop paper presents two proxy objects for high fidelity interaction in virtual reality (VR): a paper map and a smartphone. We showcase how our virtual paper map can increase interactivity and orientation, while our virtual…
Human visual attention on three-dimensional objects emerges from the interplay between bottom-up geometric processing and top-down semantic recognition. Existing 3D saliency methods rely on hand-crafted geometric features or learning-based…