Pratul P. Srinivasan

33

Papers

380

Total Citations

Papers (33)

ReconFusion: 3D Reconstruction with Diffusion Priors

Deep Multi Depth Panoramas for View Synthesis

Nuvo: Neural UV Mapping for Unruly 3D Representations

Generative Powers of Ten

Single View Refractive Index Tomography with Neural Fields

SimVS: Simulating World Inconsistencies for Robust View Synthesis

Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields

Depth From Shading, Defocus, and Correspondence Using Light-Field Angular Coherence

Light Field Blind Motion Deblurring

Aperture Supervision for Monocular Depth Estimation

Pushing the Boundaries of View Extrapolation With Multiplane Images

Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination

Learned Initializations for Optimizing Coordinate-Based Neural Representations

NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis

IBRNet: Learning Multi-View Image-Based Rendering

Gravitationally Lensed Black Hole Emission Tomography

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields

Block-NeRF: Scalable Large Scene Neural View Synthesis

HumanNeRF: Free-Viewpoint Rendering of Moving People From Monocular Video

Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields

Dense Depth Priors for Neural Radiance Fields From Sparse Input Views

Urban Radiance Fields

NeRF in the Dark: High Dynamic Range View Synthesis From Noisy Raw Images

PersonNeRF: Personalized Reconstruction From Photo Collections

Oriented Light-Field Windows for Scene Flow

Learning to Synthesize a 4D RGBD Light Field From a Single Image

Defocus Map Estimation and Deblurring From a Single Dual-Pixel Image

Baking Neural Radiance Fields for Real-Time View Synthesis

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

Eclipse: Disambiguating Illumination and Materials using Unintended Shadows

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation