3D Scene Creation and Rendering via Rough Meshes: A Lighting Transfer Avenue

TL;DR

This paper introduces LighTNet, a lighting transfer network that integrates Neural Fields Rendering with physically-based rendering, improving lighting realism in 3D scene creation using rough meshes.

Contribution

The paper proposes LighTNet, a novel lighting transfer method that bridges Neural Fields Rendering and PBR, enhancing lighting details on rough 3D models in practical workflows.

Findings

LighTNet effectively synthesizes realistic lighting on rough 3D models.

LighTNet outperforms existing methods in lighting quality and realism.

The approach improves the integration of Neural Fields into 3D rendering pipelines.

Abstract

This paper studies how to flexibly integrate reconstructed 3D models into practical 3D modeling pipelines such as 3D scene creation and rendering. Due to the technical difficulty, one can only obtain rough 3D models (R3DMs) for most real objects using existing 3D reconstruction techniques. As a result, physically-based rendering (PBR) would render low-quality images or videos for scenes that are constructed by R3DMs. One promising solution would be representing real-world objects as Neural Fields such as NeRFs, which are able to generate photo-realistic renderings of an object under desired viewpoints. However, a drawback is that the synthesized views through Neural Fields Rendering (NFR) cannot reflect the simulated lighting details on R3DMs in PBR pipelines, especially when object interactions in the 3D scene creation cause local shadows. To solve this dilemma, we propose a lighting transfer network (LighTNet) to bridge NFR and PBR, such that they can benefit from each other. LighTNet reasons about a simplified image composition model, remedies the uneven surface issue caused by R3DMs, and is empowered by several perceptual-motivated constraints and a new Lab angle loss which enhances the contrast between lighting strength and colors. Comparisons demonstrate that LighTNet is superior in synthesizing impressive lighting, and is promising in pushing NFR further in practical 3D modeling workflows.