Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing

About

In inverse rendering, accurately modeling visibility and indirect radiance for incident light is essential for capturing secondary effects. Due to the absence of a powerful Gaussian ray tracer, previous 3DGS-based methods have either adopted a simplified rendering equation or used learnable parameters to approximate incident light, resulting in inaccurate material and lighting estimations. To this end, we introduce inter-reflective Gaussian splatting (IRGS) for inverse rendering. To capture inter-reflection, we apply the full rendering equation without simplification and compute incident radiance on the fly using the proposed differentiable 2D Gaussian ray tracing. Additionally, we present an efficient optimization scheme to handle the computational demands of Monte Carlo sampling for rendering equation evaluation. Furthermore, we introduce a novel strategy for querying the indirect radiance of incident light when relighting the optimized scenes. Extensive experiments on multiple standard benchmarks validate the effectiveness of IRGS, demonstrating its capability to accurately model complex inter-reflection effects.

Chun Gu, Xiaofei Wei, Zixuan Zeng, Yuxuan Yao, Li Zhang• 2024

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisReplica
PSNR13.64
205
Novel View SynthesisScanNet++
PSNR17.48
93
Novel View SynthesisDL3DV
PSNR18.34
92
Intrinsic DecompositionHypersim
Albedo PSNR11.78
22
Novel View SynthesisFIPT synthetic dataset
PSNR22.27
16
Novel View SynthesisMipNeRF
PSNR18.72
10
Albedo EstimationNovel Synthetic Benchmark Dam Wall ↓ Harbour Sunset
PSNR23.512
9
Albedo EstimationNovel Synthetic Benchmark Chapel Day ↓ Golden Bay
PSNR24.085
9
Albedo EstimationNovel Synthetic Benchmark Golden Bay ↓ Dam Wall
PSNR21.199
9
Roughness EstimationSynthetic4Relight (test)
MSE0.008
8
Showing 10 of 58 rows

Other info

Follow for update