Pith. sign in

REVIEW 10 cited by

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

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 2410.06231 v2 pith:HAPDVDMA submitted 2024-10-08 cs.CV cs.GRcs.LG

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

classification cs.CV cs.GRcs.LG
keywords relitlrmappearancemodelunderfeed-forwardgeometryilluminationslarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting. Unlike prior inverse rendering methods requiring dense captures and slow optimization, often causing artifacts like incorrect highlights or shadow baking, RelitLRM adopts a feed-forward transformer-based model with a novel combination of a geometry reconstructor and a relightable appearance generator based on diffusion. The model is trained end-to-end on synthetic multi-view renderings of objects under varying known illuminations. This architecture design enables to effectively decompose geometry and appearance, resolve the ambiguity between material and lighting, and capture the multi-modal distribution of shadows and specularity in the relit appearance. We show our sparse-view feed-forward RelitLRM offers competitive relighting results to state-of-the-art dense-view optimization-based baselines while being significantly faster. Our project page is available at: https://relit-lrm.github.io/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. D-Rex : Diffusion Rendering for Relightable Expressive Avatars

    cs.GR 2026-04 conditional novelty 7.0

    D-Rex applies a LoRA-fine-tuned video diffusion model as an image-space post-process to add consistent relighting to any expressive full-body avatar pipeline while preserving motion and facial detail.

  2. HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

    cs.CV 2026-06 unverdicted novelty 6.0

    A framework for consistent long-horizon video relighting that propagates target latents across chunks and trains continuation via masked target-domain self-conditioning plus warm-start prompting.

  3. Extracting Neural Materials from Multi-view Images

    cs.CV 2026-06 unverdicted novelty 6.0

    NeuMatEx extracts spatially varying neural materials from multi-view images by using a learned LMRM prior for initialization followed by uncertainty-guided inverse path tracing optimization.

  4. Extracting Neural Materials from Multi-view Images

    cs.CV 2026-06 unverdicted novelty 6.0

    NeuMatEx combines a Large Material Reconstruction Model for initialization and uncertainty-guided inverse path tracing to extract spatially varying neural materials from multi-view images.

  5. Lighting-Consistent Object Transfer Across Radiance Fields

    cs.GR 2026-06 unverdicted novelty 6.0

    Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.

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

    cs.CV 2026-04 conditional novelty 6.0

    LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.

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

    cs.CV 2026-04 conditional novelty 6.0

    Scaling sparse transformer context to 20× more object tokens yields feed-forward 3D reconstructions with >2.4 dB higher PSNR and LPIPS that matches dense-view optimization.

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

    cs.CV 2026-04 conditional novelty 6.0

    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.

  9. GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures

    cs.CV 2025-12 conditional novelty 6.0

    A two-stage Gaussian-splatting inverse-rendering framework that combines monocular depth/normal, segmentation, intrinsic-image-decomposition, and diffusion priors to improve material recovery from sparse views.

  10. SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

    cs.CV 2025-12 conditional novelty 5.0

    A test-time-trained feedforward model that propagates 2D edits onto 3D Gaussian attributes at interactive speeds.