A surface photographed under even light presents nearly the same appearance from every angle; the same surface under uneven light does not. Exposure changes between views, illumination varies within a single image, and locally strong light sources leave one region bright and its neighbor in shadow. Multi-view reconstruction methods such as 3D Gaussian Splatting treat these lighting artifacts as if they were properties of the scene, entangling capture-specific illumination with the geometry and color they recover. We present EvenSplat, a framework that separates the two. EvenSplat couples an image-space illumination decomposition with an illumination field carried by the Gaussians, so that the same explanation of the lighting is shared between the two-dimensional and three-dimensional views of the scene; a camera-response network and a local exposure-compensation module absorb the global and residual differences that remain across training images. Through extensive experiments across multiple datasets and diverse forms of uneven illumination (cross-view exposure, spatial illumination variation, and high-contrast lighting) on both real-world captured and simulated benchmarks, EvenSplat generally outperforms state-of-the-art methods, particularly under high-contrast illumination.
Figures & tables
Figure 1: EvenSplat reconstructs base appearance from multi-view images with cross-view exposure variation (CEV), spatial illumination variation (SIV), and high-contrast illumination (HCI). Our method generally outperforms the state-of-the-art methods in PSNR, SSIM, and LPIPS on simulated and real-world 3D Gaussian Splatting novel view synthesis.
Figure 2: EvenSplat couples image-space decomposition with Gaussian-level illumination. Illumination alignment and image recombination connect the branches. CRN and ILEC absorb global and spatial training-image residuals. Base appearance is distinguished from the observation-fitting path.
Figure 3: Image-space regularization, from left to right: adaptive curve constraints on base-appearance intensity; edge-aware illumination smoothness; and white preservation using a bright-achromatic soft mask.
Figure 4: Gallery of the three illumination settings in the real-world and simulated datasets. CEV changes exposure across views, SIV introduces spatial illumination variation within images, and HCI produces a strong bright–dark imbalance.
Figure 5: Real-world comparisons. Columns show 3DGS, 3DGS+CHROMA, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the captured reference. Rows 1–2 show HCI, rows 3–4 SIV, and rows 5–6 CEV. EvenSplat most clearly separates appearance from illumination in the spatially uneven HCI and SIV.
Figure 6: Simulated HCI, SIV, and CEV comparisons. EvenSplat reduces illumination leakage while retaining scene texture; HCI remains the most challenging setting because contrast amplification clips information.
Figure 7: Cross-lighting appearance consistency. The capture sets differ only in left- versus right-dominant illumination. Paired appearance renderings and color-chart crops show the resulting reconstructions. PSNR is computed between corresponding left- and right-dataset appearance renderings, using one as the reference for the other; higher values indicate greater consistency across lighting conditions. PSNR (dB): 3DGS 10.5628; GS-W 10.6427; Bilateral Grid 10.3909; PPISP 10.3641; Luminance-GS 12.7311 (second-best); EvenSplat 15.5723 (best).
Figure 8: Ceiling digitization under uneven illumination ( Edwards et al., 2025 ) . Each panel pairs a held-out photograph (left) with an EvenSplat rendered novel view (right).
Appendix figures & tables7 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 9: Architecture of the image-space network for base-appearance and illumination decomposition.
Figure 10: Additional real-world qualitative comparisons. Columns show 3DGS, 3DGS+CHROMA, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the reference. The first two rows show PlasticCart (SIV), the next two show Rocks (SIV), and the final two show the extreme FourLogs case (CEV). For FourLogs , the last row applies a per-image, per-channel affine correction, yc=acxc+bc , to the preceding outputs. This diagnostic removes global color mismatch and exposes the remaining spatial reconstruction artifacts.
Figure 11: Qualitative comparison on simulated scenes under Cross-View Exposure Variation (CEV). Columns show 3DGS, 3DGS+CHROMA, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the reference; each row is a held-out view from a different scene. CEV changes the global exposure between views, testing whether each method can recover a consistent scene appearance without retaining view-dependent brightness and color shifts.
Figure 12: Qualitative comparison on simulated scenes under Spatial Illumination Variation (SIV). Columns show 3DGS, 3DGS+CHROMA, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the reference; each row is a held-out view from a different scene. The illumination changes within each image, producing adjacent bright and dark regions that cannot be removed by a single global exposure correction.
Figure 13: Qualitative comparison on simulated scenes under High-Contrast Illumination (HCI). Columns show 3DGS, 3DGS+CHROMA, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the reference; each row is a held-out view from a different scene. Strong highlights and deep shadows create clipping and severe local imbalance, emphasizing whether a method can restore shadow detail without flattening or overexposing bright regions.
Figure 14: Qualitative comparison of Rendered Observation on the four HDR-NeRF scenes. Columns show 3DGS, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the reference. The reference retains the severe but view-consistent illumination used to generate the observations; this comparison therefore measures complete-scene reconstruction fidelity rather than illumination removal.
Figure 15: Qualitative comparison of Base Appearance recovery on the four HDR-NeRF scenes. Columns show 3DGS, GS-W, Bilateral Grid, PPISP, Luminance-GS, EvenSplat, and the reference rendered under parallel uniform light. EvenSplat directly renders its decomposed base appearance, Luminance-GS produces enhanced renderings, whereas the other comparison methods contribute their standard scene renderings because they do not expose a separate base-appearance output.