Pith. sign in

REVIEW 12 cited by

GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization

Not yet reviewed by Pith; the record is open.

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

classification cs.CV
keywords gaussianrenderingilluminationinversemethodlightmaterialnormal
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

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 12 Pith papers

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

  1. Gaussian Splatting for Efficient Satellite Image Photogrammetry

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A Gaussian-splatting pipeline with affine satellite cameras, shadow mapping, and three regularizers reconstructs terrain with accuracy close to EO-NeRF in about 300x less training time.

  2. TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting

    cs.CV 2024-11 conditional novelty 7.0 of 10

    TexGaussian predicts PBR material maps directly in 3D space via octree-anchored 3D Gaussian splatting and regression, achieving roughly 20 second inference with improved multi-view consistency over diffusion-based tex...

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A feed-forward transformer reconstructs shape, PBR materials, and view-dependent radiance from 3 to 6 posed images in under a second, rivaling slower optimization-based inverse rendering.

  8. DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A single video diffusion system both estimates scene properties from video and renders photorealistic images from those properties, enabling relighting, material editing, and object insertion.

  9. HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Rendering

    cs.CV 2024-12 conditional novelty 6.0 of 10

    HDGS improves 2D Gaussian splatting with per-surfel texture maps, per-ray sorting, Fisher pruning, and five-ray frustum sampling for sharper detail and reduced aliasing.

  10. Differentiable Inverse Rendering with Interpretable Basis BRDFs

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A camera-flash inverse rendering system uses 2D Gaussians plus sparse basis materials, automatically adjusting the material count to give interpretable, separable materials.

  11. ARAP-GS: Drag-driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior

    cs.GR 2025-04 conditional novelty 5.0 of 10

    A drag-driven 3DGS editing method that applies as-rigid-as-possible deformation directly to Gaussian centers and then fine-tunes appearance with a diffusion super-resolution prior.

  12. 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