Related papers: 8DNA: 8D Neural Asset Light Transport by Distribut…
Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. However, the pretrained models are often prohibitively large…
We investigate the application of deep learning to the retrieval of the internuclear distance in the two-dimensional H$_2^{+}$ molecule from the momentum distribution of photoelectrons produced by strong-field ionization. We study the…
In this work, we propose a step towards a more accurate prediction of the environment light given a single picture of a known object. To achieve this, we developed a deep learning method that is able to encode the latent space of indoor…
In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. We propose a method to disentangle the overall model vulnerability into the sensitivity to the…
We consider the challenging problem of outdoor lighting estimation for the goal of photorealistic virtual object insertion into photographs. Existing works on outdoor lighting estimation typically simplify the scene lighting into an…
This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer…
Phase retrieval, the problem of recovering lost phase information from measured intensity alone, is an inverse problem that is widely faced in various imaging modalities ranging from astronomy to nanoscale imaging. The current process of…
3D data is a valuable asset the computer vision filed as it provides rich information about the full geometry of sensed objects and scenes. Recently, with the availability of both large 3D datasets and computational power, it is today…
Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train…
We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines. The…
Resonant transmission of light is a surface-wave assisted phenomenon that enables funneling light through subwavelength apertures milled in otherwise opaque metallic screens. In this work, we introduce a deep learning approach to…
Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hyperspectral imagery. Tasks ranging from anomaly detection to…
Most 3D neural networks are trained from scratch owing to the lack of large-scale labeled 3D datasets. In this paper, we present a novel 3D pretraining method by leveraging 2D networks learned from rich 2D datasets. We propose the…
Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts. Including 3D molecular structure as input to learned models improves their performance for many molecular tasks.…
Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve…
We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our…
Learning neural radiance fields of a scene has recently allowed realistic novel view synthesis of the scene, but they are limited to synthesize images under the original fixed lighting condition. Therefore, they are not flexible for the…
Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which…
Deep neural networks (DNNs) have recently been applied to inverse scattering problems (ISPs) due to their strong nonlinear mapping capabilities. However, supervised DNN solvers require large-scale datasets, which limits their generalization…
Machine learning has revolutionized materials discovery, but data scarcity remains a critical bottleneck for complex functional properties. As emerging systems, two-dimensional (2D) materials possess limited overall data volumes. Evaluating…