37 citations · 61 across the 18 of their papers we have counts for
21 papers
TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolution
Zhiming Hu, Ran Zhang, Angela Ye +7
Diffusion models have achieved remarkable success in image super-resolution (SR) by leveraging strong generative priors to enhance perceptual quality. However, for textual content,…
Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising
Mohammad Mohammadi, Sina Honari, Stavros Tsogkas +6
Raw images inherently suffer from noise due to the stochastic nature of light and sensor hardware imperfections. As real photon counts fall, the ratio of this noise to the signal d…
BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors
Dong Huo, Tristan Aumentado-Armstrong, Samrudhdhi B. Rangrej +8
Burst image super resolution (BISR) aims to construct a single high-resolution (HR) image by aggregating information from multiple low-resolution (LR) frames, relying on temporal r…
Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks
Abhinav Kumar, Tristan Aumentado-Armstrong, Lazar Valkov +4
Gaussian Splatting has revolutionized the field of Novel View Synthesis (NVS) with faster training and real-time rendering. However, its reconstruction fidelity still trails behind…
Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution
Weiming Ren, Raghav Goyal, Zhiming Hu +3
Generative super-resolution (GSR) currently sets the state-of-the-art in terms of perceptual image quality, overcoming the "regression-to-the-mean" blur of prior non-generative mod…
Augmenting Perceptual Super-Resolution via Image Quality Predictors
Fengjia Zhang, Samrudhdhi B. Rangrej, Tristan Aumentado-Armstrong +2
Super-resolution (SR), a classical inverse problem in computer vision, is inherently ill-posed, inducing a distribution of plausible solutions for every input. However, the desired…
Learn Your Scales: Towards Scale-Consistent Generative Novel View Synthesis
Fereshteh Forghani, Jason J. Yu, Tristan Aumentado-Armstrong +2
Conventional depth-free multi-view datasets are captured using a moving monocular camera without metric calibration. The scales of camera positions in this monocular setting are am…
Geometry-Aware Diffusion Models for Multiview Scene Inpainting
Ahmad Salimi, Tristan Aumentado-Armstrong, Marcus A. Brubaker +1
In this paper, we focus on 3D scene inpainting, where parts of an input image set, captured from different viewpoints, are masked out. The main challenge lies in generating plausib…
Probabilistic Directed Distance Fields for Ray-Based Shape Representations
Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson +1
In modern computer vision, the optimal representation of 3D shape continues to be task-dependent. One fundamental operation applied to such representations is differentiable render…
PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis
Jason J. Yu, Tristan Aumentado-Armstrong, Fereshteh Forghani +2
This paper considers the problem of generative novel view synthesis (GNVS), generating novel, plausible views of a scene given a limited number of known views. Here, we propose a s…
Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations
Tristan Aumentado-Armstrong, Ashkan Mirzaei, Marcus A. Brubaker +4
Neural Radiance Fields (NeRFs) have proven to be powerful 3D representations, capable of high quality novel view synthesis of complex scenes. While NeRFs have been applied to graph…
Watch Your Steps: Local Image and Scene Editing by Text Instructions
Ashkan Mirzaei, Tristan Aumentado-Armstrong, Marcus A. Brubaker +4
Denoising diffusion models have enabled high-quality image generation and editing. We present a method to localize the desired edit region implicit in a text instruction. We levera…
Reference-guided Controllable Inpainting of Neural Radiance Fields
Ashkan Mirzaei, Tristan Aumentado-Armstrong, Marcus A. Brubaker +4
The popularity of Neural Radiance Fields (NeRFs) for view synthesis has led to a desire for NeRF editing tools. Here, we focus on inpainting regions in a view-consistent and contro…
SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields
Ashkan Mirzaei, Tristan Aumentado-Armstrong, Konstantinos G. Derpanis +4
Neural Radiance Fields (NeRFs) have emerged as a popular approach for novel view synthesis. While NeRFs are quickly being adapted for a wider set of applications, intuitively editi…
Representing 3D Shapes with Probabilistic Directed Distance Fields
Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson +1
Differentiable rendering is an essential operation in modern vision, allowing inverse graphics approaches to 3D understanding to be utilized in modern machine learning frameworks.…
GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
Vineeth S. Bhaskara, Tristan Aumentado-Armstrong, Allan Jepson +1
Modern generative adversarial networks (GANs) predominantly use piecewise linear activation functions in discriminators (or critics), including ReLU and LeakyReLU. Such models lear…
Towards Robust Bisimulation Metric Learning
Mete Kemertas, Tristan Aumentado-Armstrong
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and in…
Disentangling Geometric Deformation Spaces in Generative Latent Shape Models
Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson +1
A complete representation of 3D objects requires characterizing the space of deformations in an interpretable manner, from articulations of a single instance to changes in shape ac…
Cycle-Consistent Generative Rendering for 2D-3D Modality Translation
Tristan Aumentado-Armstrong, Alex Levinshtein, Stavros Tsogkas +2
For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that l…
Geometric Disentanglement for Generative Latent Shape Models
Tristan Aumentado-Armstrong, Stavros Tsogkas, Allan Jepson +1
Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun t…
Latent Molecular Optimization for Targeted Therapeutic Design
Tristan Aumentado-Armstrong
We devise an approach for targeted molecular design, a problem of interest in computational drug discovery: given a target protein site, we wish to generate a chemical with both hi…