Related papers: See the past: Time-Reversed Scene Reconstruction f…
Fire effects are widely used in various computer graphics applications such as visual effects and video games. Modeling the shape and appearance of fire phenomenon is challenging as the underlying effects are driven by complex laws of…
Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack…
Environments in Reinforcement Learning are usually only partially observable. To address this problem, a possible solution is to provide the agent with information about the past. However, providing complete observations of numerous steps…
Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution. This is unlikely in real-world long-range surveillance systems, since humans are distant from the cameras. To…
The detailed knowledge of the inner skin temperature behavior is very important to evaluate and manage the aging of large pipes in cooling systems. We describe here a method to obtain this information as a function of outer skin temperature…
Urban areas are increasingly vulnerable to thermal extremes driven by rapid urbanization and climate change. Traditionally, thermal extremes have been monitored using Earth-observing satellites and numerical modeling frameworks. For…
Augmenting pretrained language models (LMs) with a vision encoder (e.g., Flamingo) has obtained the state-of-the-art results in image-to-text generation. However, these models store all the knowledge within their parameters, thus often…
We introduce Deep Thermal Imaging, a new approach for close-range automatic recognition of materials to enhance the understanding of people and ubiquitous technologies of their proximal environment. Our approach uses a low-cost mobile…
Our world is not static and humans naturally cause changes in their environments through interactions, e.g., opening doors or moving furniture. Modeling changes caused by humans is essential for building digital twins, e.g., in the context…
Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for time series analysis…
We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films. Instead of performing frame-wise restoration, our method is based on the hidden knowledge learned from adjacent frames that…
We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view…
Can we improve detection in the thermal domain by borrowing features from rich domains like visual RGB? In this paper, we propose a pseudo-multimodal object detector trained on natural image domain data to help improve the performance of…
Existing methods for reconstructing interactive scenes primarily focus on replacing reconstructed objects with CAD models retrieved from a limited database, resulting in significant discrepancies between the reconstructed and observed…
Inverse rendering aims to reconstruct geometry and reflectance of objects from images. Despite recent progress, existing methods often produces inaccurate reconstructions that are sensitive to ambient illumination conditions. Here we…
Humans can infer the missing parts of an occluded object by leveraging prior knowledge and visible cues. However, enabling deep learning models to accurately predict such occluded regions remains a challenging task. De-occlusion addresses…
Cross modal face matching between the thermal and visible spectrum is a much de- sired capability for night-time surveillance and security applications. Due to a very large modality gap, thermal-to-visible face recognition is one of the…
Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…
Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework…
Thermo- and photo- acoustic tomography require reconstructing initial acoustic pressure in a body from time series of pressure measured on a surface surrounding the body. For the classical case of free space wave propagation, various…