33 citations · 50 across the 11 of their papers we have counts for
11 papers
WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Concepts
Rishi Upadhyay, Howard Zhang, Jim Solomon +5
Recent advances in generative foundational models, often termed "world models," have propelled interest in applying them to critical tasks like robotic planning and autonomous syst…
All-day Depth Completion
Vadim Ezhov, Hyoungseob Park, Zhaoyang Zhang +7
We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tac…
GT-Rain Single Image Deraining Challenge Report
Howard Zhang, Yunhao Ba, Ethan Yang +20
This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023. The aim of this competition is to study the rainy weather phen…
WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weather
Blake Gella, Howard Zhang, Rishi Upadhyay +5
The introduction of large, foundational models to computer vision has led to drastically improved performance on the task of semantic segmentation. However, these existing methods…
Enhancing Diffusion Models with 3D Perspective Geometry Constraints
Rishi Upadhyay, Howard Zhang, Yunhao Ba +5
While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent d…
MIME: Minority Inclusion for Majority Group Enhancement of AI Performance
Pradyumna Chari, Yunhao Ba, Shreeram Athreya +1
Several papers have rightly included minority groups in artificial intelligence (AI) training data to improve test inference for minority groups and/or society-at-large. A society-…
Not Just Streaks: Towards Ground Truth for Single Image Deraining
Yunhao Ba, Howard Zhang, Ethan Yang +8
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image. As th…
Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation
Yunhao Ba, Zhen Wang, Kerim Doruk Karinca +2
Camera-based remote photoplethysmography (rPPG) provides a non-contact way to measure physiological signals (e.g., heart rate) using facial videos. Recent deep learning architectur…
Visual Physics: Discovering Physical Laws from Videos
Pradyumna Chari, Chinmay Talegaonkar, Yunhao Ba +1
In this paper, we teach a machine to discover the laws of physics from video streams. We assume no prior knowledge of physics, beyond a temporal stream of bounding boxes. The probl…
Blending Diverse Physical Priors with Neural Networks
Yunhao Ba, Guangyuan Zhao, Achuta Kadambi
Machine learning in context of physical systems merits a re-examination of the learning strategy. In addition to data, one can leverage a vast library of physical prior models (e.g…
Deep Shape from Polarization
Yunhao Ba, Alex Ross Gilbert, Franklin Wang +6
This paper makes a first attempt to bring the Shape from Polarization (SfP) problem to the realm of deep learning. The previous state-of-the-art methods for SfP have been purely ph…