Pith. sign in

REVIEW 5 cited by

GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.05133 v2 pith:XYZA5R6V submitted 2023-12-08 cs.CV

Yahao Shi , Yanmin Wu , Chenming Wu , Xing Liu , Chen Zhao , Haocheng Feng , Jian Zhang , Bin Zhou
show 2 more authors
Errui Ding Jingdong Wang
This is my paper · ORCID
classification cs.CV
keywords gaussianrenderingilluminationinversemethodlightmaterialnormal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geometry. The key contributions lie in three-fold. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-bounce light transport. To further enhance the illumination disentanglement, we represent a high-resolution environmental map with a learnable low-resolution map and a lightweight, fully convolutional network. Our method achieves state-of-the-art performance in both relighting and novel view synthesis tasks among the recently proposed inverse rendering methods while achieving real-time rendering. This substantiates our proposed method's efficacy and broad applicability, highlighting its potential as an influential tool in various real-time interactive graphics applications such as material editing and relighting. The code will be released at https://github.com/guduxiaolang/GIR.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Scaling transformer context with sparse attention and 3D-aware block routing improves feed-forward 3D reconstruction and inverse rendering, closing much of the quality gap with dense-view optimization.

  2. InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling

    cs.CV 2025-07 conditional novelty 6.0 of 10

    InvRGB+L jointly estimates visible and LiDAR albedo with a physics-based specular LiDAR model and cross-modal consistency losses, improving inverse rendering and LiDAR intensity simulation for urban and indoor scenes.

  3. Gaussian Splatting with Discretized SDF for Relightable Assets

    cs.GR 2025-07 conditional novelty 6.0 of 10

    A per-Gaussian discretized SDF with a projection-based consistency loss improves decomposition quality and relighting in Gaussian splatting, beating Gaussian-based baselines while using less memory.

  4. UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Jointly predicting albedo and relit appearance with one video-diffusion pass improves relighting fidelity and generalization over two-stage inverse-plus-forward pipelines.

  5. BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video

    cs.GR 2025-02 conditional novelty 5.0 of 10

    A pipeline that adds physically-based surface materials to dynamic 4D Gaussians, producing relightable volumetric video from multi-view RGB footage.

Pith tools