LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement

Yang Ye; Jiajun Ma; Chen Wu; Wei Wang; Dianjie Lu; Guijuan Zhang; Linwei Fan; Zhuoran Zheng

cs.CVSep 27, 2026

LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement

Authors: Yang Ye, Jiajun Ma, Chen Wu, Wei Wang, Dianjie Lu, Guijuan Zhang, Linwei Fan, Zhuoran Zheng

Organizations: Universiti Sains Malaysia · National University of Defense Technology · Sun Yat-sen University · Shandong Normal University · Shandong University of Finance and Economics

Abstract

Color enhancement of 4K images must meet a quality target under a tight compute budget. Three-dimensional lookup tables (3D LUTs) dominate real-time enhancement because they decide at low resolution and apply a per-pixel lookup at full resolution. A single global LUT, however, is spatially invariant, so an underexposed shadow and a well-exposed region that share a pixel value receive identical corrections. Spatially heterogeneous demands cannot be expressed by such a mapping. We propose LoopLUT, a region-cascaded 3D LUT with progressive refinement. A global LUT performs the overall correction, followed by K-1 loop iterations. In each iteration a gating head predicts at low resolution the region that still needs correction, then builds a residual LUT from the color statistics of that region alone. The cascaded gates form a partition of unity, so the output is a per-pixel convex combination of the K lookup results. Fusion is therefore performed by the gates themselves, with no separate fusion module and no interpolation error accumulating across rounds. The decision stage runs at a fixed 256x256 resolution, independent of output resolution, so a 4K image costs only K pure lookups. Extensive experiments across four benchmarks show that LoopLUT improves PSNR by up to 2.81 dB over the strongest prior method, while keeping real-time throughput at 4K. The same decomposition also generalizes well to underwater enhancement datasets.

Figures & tables

Figure 1: LoopLUT divides an image among its correction rounds. (a) An LCDP test image. (b–d) Partition weights from the trained gates of LoopLUT (

K{=}3

), shown without contrast stretching; color saturation encodes the weight.

\mathbf{A}_{k}(x)

is the share of pixel

x

taken from the lookup of round

k

. The means (0.65, 0.20 and 0.15) show that the global round covers most of the image and later rounds refine ever smaller regions. Each weight is what the cascade passes to round

k

minus what round

k

passes on,

\mathbf{A}_{k}{=}\mathbf{C}_{k}(1{-}\mathbf{m}_{k+1})

, where

\mathbf{C}_{k}

is the product of the gates up to round

k

. The weights are therefore non-negative and sum to one at every pixel, so the output is a convex blend of the

K

lookups. (e) Profile along the dashed scanline, confirming the unit sum and smooth transitions.

Figure 2: Overall architecture of LoopLUT ( $\mathbf{M}_{n}$ , $\mathbf{C}_{n}$ and $\mathbf{T}_{n}$ in the figure are $\mathbf{m}_{k}$ , $\mathbf{C}_{k}$ and $\mathbf{T}_{k}$ in the text). The global round (gray) passes the $256\times 256$ input once through the Color UNet to give the global feature $\mathbf{F}_{\text{g}}$ (VectorG) and the decoder feature map $\mathbf{D}$ (Feature map), which an MLP turns into the global LUT $\mathbf{T}_{1}$ by mixing the basis LUTs $\mathbf{B}_{1},\dots,\mathbf{B}_{5}$ . Each region round (blue, $\times K{-}1$ ) area-pools its inputs to the $s\times s$ gate bottleneck, predicts the gate $\mathbf{M}_{n}$ , multiplies it into the cumulative gate $\mathbf{C}_{n}$ , and generates $\mathbf{T}_{n}$ from masked statistics inside $\mathbf{C}_{n}$ . At execution the $K$ LUTs are applied to the original image and combined per pixel by the partition weights, so the gates are the fusion. The decision stage is fixed at low resolution throughout.

		LCDP				MIT-Adobe FiveK				Mobile-Spec
Method	Venue	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	CIEDE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	CIEDE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	CIEDE $\downarrow$
HDRNet	SIGGRAPH’17	21.75	0.8265	0.1860	10.98	20.57	0.7251	0.0960	9.10	20.34	0.7911	0.1652	6.57
RUAS	CVPR’21	18.25	0.7568	0.2065	9.11	19.29	0.7095	0.1393	9.86	12.22	0.7470	0.1833	17.26
LCDPNet	ECCV’22	23.29	0.8423	0.1587	8.43	15.13	0.6029	0.2437	17.17	25.25	0.9097	0.1404	5.21
AdaInt	CVPR’22	20.93	0.7856	0.2258	9.42	18.76	0.7235	0.1474	12.21	26.98	0.9264	0.0850	4.02
LightenDiffusion	ECCV’24	19.04	0.7743	0.1334	9.33	18.35	0.7050	0.1542	12.35	23.23	0.8383	0.2759	7.31

Table 1: Quantitative comparison with state-of-the-art methods on LCDP, MIT-Adobe FiveK and Mobile-Spec. In each column the best is bold and the second best is underlined;

\uparrow

\downarrow

indicates that higher/lower is better.

Panel of Figure 3 — Figure 3: Qualitative comparison on the LCDP test set. Each panel shows the full output above and, below, the magnified red and green crops, placed on the two middle paintings and on the steel frame at the top; the red box examines midtone color reproduction and the green box detail recovery in dark structure. All methods use the same crops.

Panel of Figure 4 — Figure 4: Qualitative comparison on the MIT-Adobe FiveK test set. Layout as in Figure 3 ; the red crop covers the face of a stone head and the green crop the weathered stone of its crown, examining the light-to-dark transition across the face and texture preservation on the highlight side.

Panel of Figure 5 — Figure 5: Qualitative comparison on the Mobile-Spec test set. Layout as in Figure 3 ; the red crop covers the sunlit facade and the green crop the backlit region at lower left, examining color reproduction under warm illumination and tonal separation in the backlit building and tree canopy.

Resolution	Pixels	GFLOPs			Latency			Device memory
	(MP)	Decide	Exec	Total	Decide	Total	Through-	Peak	Traffic	Band-
					(ms)	(ms)	put (FPS)	(MB)	(MB)	width (GB/s)
$1620\times 1080$ (LCDP native)	1.75	6.135	0.362	6.497	1.84	5.10	196	93	774	159
$1920\times 1080$ (FHD)	2.07	6.135	0.429	6.564	1.84	5.67	176	104	880	163
$3840\times 2160$ (4K)	8.29	6.135	1.717	7.852	1.84	16.23	62	296	2914	188

Table 3: Resolution scaling and memory behavior of LoopLUT. The decision stage is constant at 6.135 GFLOPs and 1.84 ms at every resolution ; only the pure-lookup execution stage grows with pixel count. Traffic is the per-frame device-memory read

{+}

write volume of the current unfused implementation, and Bandwidth is that volume divided by the measured latency.

Panel of Table 4 — Table 4: LSUI underwater benchmark. Best in bold, second underlined; compared methods quoted from public reports.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Method	Venue	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	CIEDE $\downarrow$
HDRNet	SIGGRAPH’17	20.89	0.7809	0.1491	8.88
RUAS	CVPR’21	16.59	0.7378	0.1764	12.08
LCDPNet	ECCV’22	21.22	0.7850	0.1809	10.27
AdaInt	CVPR’22	22.22	0.8118	0.1527	8.55
LightenDiffusion	ECCV’24	20.21	0.7725	0.1878	9.66
CSEC	CVPR’24	20.12	0.7748	0.1962	11.62

Appendix

Table 5: Average over LCDP, MIT-Adobe FiveK and Mobile-Spec of the metrics in Table 1 . In each column the best is bold and the second best is underlined.

Figure 9: The averages of Table 5 , with methods sorted from best to worst in each panel; the arrow marks the gap between LoopLUT and the runner-up.

Panel of Figure 10 — Figure 10: Visual comparison on four LSUI test images, one image per row. The compared methods are those of Table 8 .

Panel of Figure 11 — Figure 11: Real-world smartphone photographs. Top: an underexposed indoor scene; middle: a night scene with blown-out street lamps (same crop for all methods). Bottom: NIQE against latency (left) and averages over the two photographs (right; best in bold).

Figure 12: Mobile deployment. LoopLUT runs on an Android phone through the ONNX Runtime CPU backend, with three tabs corresponding to (a) input, (b) enhanced output and (c) partition assignment. The colors in (c) are the partition weights of Equation ( 1 ): green for the global round $\mathbf{A}_{1}$ , yellow for $\mathbf{A}_{2}$ and red for $\mathbf{A}_{3}$ , displayed after per-image contrast stretching; the three thumbnails below can be tapped to enlarge. The bottom of the interface shows the measured readout for that particular run : Decide 129 ms, Render 52 ms, total 198 ms. On-device total time fluctuates between roughly 100 and 200 ms depending on the input photograph. Decide corresponds to the fixed-resolution decision stage and Render to the execution stage that grows with pixel count, matching the split in Table 3 .

Explore similar work

DY-LUT: Depth-Aware YCbCr Lookup Tables for Real-Time Underwater Image Enhancement
Jul 24, 2026Cunhao Zhu, Xiangtao Kong, Dongliang Xu +3Underwater Image Enhancement Methods Visual Degradation
1Shandong University · 2The Hong Kong Polytechnic University · 3Mohamed bin Zayed University of Artificial Intelligence
PrefLUT: Reusable and Refinable Personalized Color Editing from Pairwise Preferences
Sep 28, 2026Chuanzhi Xu, Langyi Chen, Chengkun Yue +5Image Editing Preference Alignment Learning
The University of Sydney · Indiana University · The University of Hong Kong
Hybrid-LUT: Channel-Aware Hybrid Lookup Table and Filtering for Efficient Image Denoising
Aug 12, 2026Zhilin Ai, Boyu Li, Sidi Yang +5Iterative Denoising Methods Red-Green-Blue
The University of Hong Kong

Jul 24, 2026, eess.IVJ/K move · Enter open · S save

DY-LUT: Depth-Aware YCbCr Lookup Tables for Real-Time Underwater Image Enhancement

Cunhao Zhu, Xiangtao Kong, Dongliang Xu, Zhiheng Zhang+2

1Shandong University · 2The Hong Kong Polytechnic University · 3Mohamed bin Zayed University of Artificial Intelligence

Underwater Image Enhancement Methods Visual Degradation

Open paper AskPDF arXiv

Underwater image enhancement is challenged by spatially non-uniform, wavelength-dependent attenuation. Propagation distance and wavelength govern this degradation, while YCbCr separates luminance from chrominance for restoration. We propose DY-LUT, a depth-aware YCbCr lookup-table framework for real-time enhancement. A dual-branch encoder predicts image-level fusion weights and a joint pair of pixel-wise degradation indices from image and depth features. These quantities condition learnable 4D LUTs, followed by lightweight local refinement. DY-LUT preserves traditional LUT efficiency while enabling depth-conditioned, spatially adaptive restoration. With externally supplied depth, its 3.56M-parameter enhancement network achieves competitive quality on UIEB-90 and LSUI and runs

9

304\times

faster than representative high-capacity baselines. Adaptive inference further maintains real-time performance (

\sim7

ms) for 4K UIQAD images. DY-LUT also benefits downstream detection and feature matching. Ablations show that YCbCr is a more effective basis than RGB for depth-conditioned lookup, while the jointly learned indices further improve adaptive querying. These results provide a physically grounded route to efficient UIE on practical platforms.

Abstract

Explore similar work

DY-LUT: Depth-Aware YCbCr Lookup Tables for Real-Time Underwater Image Enhancement

PrefLUT: Reusable and Refinable Personalized Color Editing from Pairwise Preferences

Hybrid-LUT: Channel-Aware Hybrid Lookup Table and Filtering for Efficient Image Denoising