We propose an uncertainty-aware video compression model that effectively captures the predictive uncertainty with deep ensembles and saves bits by more than 20% when compared to DVC Pro.

We propose 3D-DST that generates synthetic data with 3D groundtruth by incorporating 3D geomeotry control into diffusion models. With our diverse prompt generation, we effectively improve both in-distribution (ID) and out-of-distribution (OOD) performance for various 2D and 3D vision tasks.

We introduce Super-CLEVR-3D, a compositional reasoning dataset that contains questions about object parts, their 3D poses, and occlusions. We propose PO3D-VQA, a 3D-aware VQA model that combines probabilistic neural symbolic program execution with 3D generative representations of objects.

We introduce Neural Textured Deformable Meshes (NTDM), which learns a neural mesh model with deformable geometry and enables optimization on both camera parameters and object geometries.

We introduce SyntheticP3D, a synthetic dataset for object pose estimation, and CC3D that adapts neural mesh models from synthetic to real data.

Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model.

We introduce Super-CLEVR, where different factors in VQA domain shifts can be isolated in order that their effects can be studied independently. We propose probabilistic NSVQA (P-NSVQA), which extends NSVQA with uncertainty reasoning.

We introduce a coarse-to-fine optimization strategy that utilizes the rendering process to estimate a sparse set of 6D object proposals, which are subsequently refined with gradient-based optimization.

We introduce ROBIN, a benchmark dataset for diagnosing the robustness of 2D and 3D vision algorithms to individual nuisances in real-world images.

We present a novel pluralistic building contour completion framework, which uses an entropy-based model to request information from the user for the next most informative location in the image.

We propose a framework for making group decisions from natural language-based preferences. Experiments on the real world data confirms the efficacy of our method.

Characterize 10 different microstructure representations with image texture features and quantitative metrics from image segmentation. For the microstructure generation task, two schemes are considered: 1) generating high-resolution (1024x1024) microstructure images from random noise; and 2) train a style transfer GAN for image generation conditioned on the segmentation label.

Kinetic modeling of a discontinuous precipitation reaction (5 phases) by 1) deep learning with CNN, and 2) performing image segmentation of various microstructure and quantizing the area fractions.

We first review the application of image-driven machine learning approaches to the field of materials characterization. Then we analyze and discuss the impact of various approaches at each step of the experiments.