724 citations · 1.3k across the 25 of their papers we have counts for
27 papers
PureLight: Learning Complex Luminaires with Light Tracing
Pedro Figueiredo, Zixuan Li, Beibei Wang +2
We propose a neural formulation for estimating the appearance of complex luminaires. We focus on challenging luminaires with complex light transport (e.g., small emitters enclosed…
ReAge3D: Re-Aging 3D Faces with View Consistency
Libing Zeng, Li Ma, Mingming He +3
We present a novel framework for realistic and controllable 3D face re-aging which produces highly detailed, identity-preserving results. Existing 3D editing methods, while effecti…
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
Xilong Zhou, Bao-Huy Nguyen, Zheng Zeng +6
Video generative models have achieved remarkable progress in synthesizing photorealistic video sequences. However, enabling broader and more creative downstream applications requir…
EfficientDepth: A Fast and Detail-Preserving Monocular Depth Estimation Model
Andrii Litvynchuk, Ivan Livinsky, Anand Ravi +2
Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advanceme…
RealMat: Realistic Materials with Diffusion and Reinforcement Learning
Xilong Zhou, Pedro Figueiredo, Miloš Hašan +4
Generative models for high-quality materials are particularly desirable to make 3D content authoring more accessible. However, the majority of material generation methods are train…
Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards
Aakash Garg, Libing Zeng, Andrii Tsarov +1
In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a di…
Neural Path Guiding with Distribution Factorization
Pedro Figueiredo, Qihao He, Nima Khademi Kalantari
In this paper, we present a neural path guiding method to aid with Monte Carlo (MC) integration in rendering. Existing neural methods utilize distribution representations that are…
RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors
Avinash Paliwal, Xilong Zhou, Wei Ye +3
In this paper, we propose RI3D, a novel 3DGS-based approach that harnesses the power of diffusion models to reconstruct high-quality novel views given a sparse set of input images.…
PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion
Avinash Paliwal, Xilong Zhou, Andrii Tsarov +1
In this paper, we present PanoDreamer, a novel method for producing a coherent 360° 3D scene from a single input image. Unlike existing methods that generate the scene sequentially…
Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators
Libing Zeng, Nima Khademi Kalantari
With the advances in generative adversarial networks (GANs) and neural rendering, 3D relightable face generation has received significant attention. Among the existing methods, a p…
PanDORA: Casual HDR Radiance Acquisition of Indoor Scenes for Image-based Lighting
Mohammad Reza Karimi Dastjerdi, Dominique Tanguay-Gaudreau, Frédéric Fortier-Chouinard +3
Most novel view synthesis methods -- including Neural Radiance Fields (NeRF) -- struggle to capture the high dynamic range (HDR) radiance required for realistic image-based lightin…
CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
Avinash Paliwal, Wei Ye, Jinhui Xiong +4
The field of 3D reconstruction from images has rapidly evolved in the past few years, first with the introduction of Neural Radiance Field (NeRF) and more recently with 3D Gaussian…
ReShader: View-Dependent Highlights for Single Image View-Synthesis
Avinash Paliwal, Brandon Nguyen, Andrii Tsarov +1
In recent years, novel view synthesis from a single image has seen significant progress thanks to the rapid advancements in 3D scene representation and image inpainting techniques.…
MyStyle++: A Controllable Personalized Generative Prior
Libing Zeng, Lele Chen, Yi Xu +1
In this paper, we propose an approach to obtain a personalized generative prior with explicit control over a set of attributes. We build upon MyStyle, a recently introduced method,…
PhotoMat: A Material Generator Learned from Single Flash Photos
Xilong Zhou, Miloš Hašan, Valentin Deschaintre +4
Authoring high-quality digital materials is key to realism in 3D rendering. Previous generative models for materials have been trained exclusively on synthetic data; such data is l…
Implicit View-Time Interpolation of Stereo Videos using Multi-Plane Disparities and Non-Uniform Coordinates
Avinash Paliwal, Andrii Tsarov, Nima Khademi Kalantari
In this paper, we propose an approach for view-time interpolation of stereo videos. Specifically, we build upon X-Fields that approximates an interpolatable mapping between the inp…
Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing
Salah A Faroughi, Nikhil Pawar, Celio Fernandes +4
Recent breakthroughs in computing power have made it feasible to use machine learning and deep learning to advance scientific computing in many fields, including fluid mechanics, s…
Frame Interpolation for Dynamic Scenes with Implicit Flow Encoding
Pedro Figueirêdo, Avinash Paliwal, Nima Khademi Kalantari
In this paper, we propose an algorithm to interpolate between a pair of images of a dynamic scene. While in the past years significant progress in frame interpolation has been made…
TileGen: Tileable, Controllable Material Generation and Capture
Xilong Zhou, Miloš Hašan, Valentin Deschaintre +3
Recent methods (e.g. MaterialGAN) have used unconditional GANs to generate per-pixel material maps, or as a prior to reconstruct materials from input photographs. These models can…
Differentiable Simulation of Inertial Musculotendons
Ying Wang, Jasper Verheul, Sang-Hoon Yeo +2
We propose a simple and practical approach for incorporating the effects of muscle inertia, which has been ignored by previous musculoskeletal simulators in both graphics and biome…
Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask
Avinash Paliwal, Libing Zeng, Nima Khademi Kalantari
In this paper, we propose a learning-based approach for denoising raw videos captured under low lighting conditions. We propose to do this by first explicitly aligning the neighbor…
Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss
Marcel Santana Santos, Tsang Ing Ren, Nima Khademi Kalantari
Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruct…
Deep Slow Motion Video Reconstruction with Hybrid Imaging System
Avinash Paliwal, Nima Khademi Kalantari
Slow motion videos are becoming increasingly popular, but capturing high-resolution videos at extremely high frame rates requires professional high-speed cameras. To mitigate this…
Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines
Ben Mildenhall, Pratul P. Srinivasan, Rodrigo Ortiz-Cayon +4
We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration. Previous approaches either re…