Skip to content

Latest commit

 

History

History
41 lines (37 loc) · 2.61 KB

README.md

File metadata and controls

41 lines (37 loc) · 2.61 KB
Raw

Neural View Synthesis and Appearance Editing from Unstructured Images

Indian Conference on Computer Vision, Graphics and Image Processing

1CVIT, IIIT Hyderabad

Abstract
We present a neural rendering framework for simultaneous view synthesis and appearance editing of a scene from multi-view images captured under known environment illumination. Existing approaches either achieve view synthesis alone or view synthesis along with relighting, without direct control over the scene’s appearance. Our approach explicitly disentangles the appearance and learns a lighting representation that is independent of it. Specifically, we independently estimate the BRDF and use it to learn a lighting-only representation of the scene. Such disentanglement allows our approach to generalize to arbitrary changes in appearance while performing view synthesis. We show results of editing the appearance of a real scene, demonstrating that our approach produces plausible appearance editing. The performance of our view synthesisapproach is demonstrated to be at par with state-of-the-art approaches on both real and synthetic data.

Code Instructions

Prerequisites

This code was tested on UBuntu 20.04, with Python 3.8. For running the code we used pytorch 3.8. Please check requirements.txt for other dependencies

Preprocess the Data

Checkout preprocess for instructions on how to generate and preprocess the data.

Running code

  • DNR for instructions on how to run DNR code.
  • Independent for instructions on how to run code with independent optimization.
  • Joint for instructions on how to run code with joint optimization.