Browsing by Author "Kalantari, Nima Khademi"
Now showing items 1-6 of 6
-
Adversarial Single-Image SVBRDF Estimation with Hybrid Training
Zhou, Xilong; Kalantari, Nima Khademi (The Eurographics Association and John Wiley & Sons Ltd., 2021)In this paper, we propose a deep learning approach for estimating the spatially-varying BRDFs (SVBRDF) from a single image. Most existing deep learning techniques use pixel-wise loss functions which limits the flexibility ... -
Deep HDR Video from Sequences with Alternating Exposures
Kalantari, Nima Khademi; Ramamoorthi, Ravi (The Eurographics Association and John Wiley & Sons Ltd., 2019)A practical way to generate a high dynamic range (HDR) video using off-the-shelf cameras is to capture a sequence with alternating exposures and reconstruct the missing content at each frame. Unfortunately, existing ... -
Semantic-Aware Generative Approach for Image Inpainting
Chanda, Deepankar; Kalantari, Nima Khademi (The Eurographics Association, 2021)We propose a semantic-aware generative method for image inpainting. Specifically, we divide the inpainting process into two tasks; estimating the semantic information inside the masked areas and inpainting these regions ... -
A Semi‐Procedural Convolutional Material Prior
Zhou, Xilong; Hašan, Miloš; Deschaintre, Valentin; Guerrero, Paul; Sunkavalli, Kalyan; Kalantari, Nima Khademi (© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023)Lightweight material capture methods require a material prior, defining the subspace of plausible textures within the large space of unconstrained texel grids. Previous work has either used deep neural networks (trained ... -
Test‐Time Optimization for Video Depth Estimation Using Pseudo Reference Depth
Zeng, Libing; Kalantari, Nima Khademi (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023)In this paper, we propose a learning‐based test‐time optimization approach for reconstructing geometrically consistent depth maps from a monocular video. Specifically, we optimize an existing single image depth estimation ... -
Variational Pose Prediction with Dynamic Sample Selection from Sparse Tracking Signals
Milef, Nicholas; Sueda, Shinjiro; Kalantari, Nima Khademi (The Eurographics Association and John Wiley & Sons Ltd., 2023)We propose a learning-based approach for full-body pose reconstruction from extremely sparse upper body tracking data, obtained from a virtual reality (VR) device. We leverage a conditional variational autoencoder with ...