SEE Challenge 2026: Event-Guided Brightness Adjustment Across a Broad Illumination Range

Yunfan Lu; Mingchao Xu; Hanyu Zhou; Shaoyu Liu; Haoyue Liu; Peiqi Duan; Shihan Peng; Yinqiang Zheng

cs.CVSep 24, 2026

SEE Challenge 2026: Event-Guided Brightness Adjustment Across a Broad Illumination Range

Authors: Yunfan Lu, Mingchao Xu, Hanyu Zhou, Shaoyu Liu, Haoyue Liu, Peiqi Duan, Shihan Peng, Yinqiang Zheng, +4 more

Organizations: Hong Kong University of Science and Technology (Guangzhou) · National University of Singapore · Xidian University · Tsinghua University · Huazhong University of Science and Technology · Peking University · The University of Tokyo · Robotics and Perception Group, University of Zurich

Abstract

Event cameras provide a high dynamic range and preserve brightness-change cues in lighting conditions where conventional RGB frames may be noisy or saturated. To benchmark event-guided restoration across a broad illumination range, we organized the SEE Challenge 2026 with the Event-Based Multimodal Vision Workshop at ECCV 2026. The task conditions restoration on one or more RGB frames, synchronized events, and a scalar target-brightness statistic provided by the organizers. It uses SEE-600K, which contains 610,126 image-event observations from 202 real-world scenes spanning low-light, normal-light, and high-light conditions with illumination variations of up to 1,000 $\times$ . The challenge follows an open-system protocol: participants may use different temporal contexts, architectures, pretrained weights, test-time augmentation, and post-processing strategies. PSNR determines the ranking, and SSIM is reported as a secondary metric. Around 70 teams registered interest and 15 valid CodaBench submissions were received. Six distinct teams completed organizer-side identity and technical verification, provided method descriptions, checkpoints, inference code, and instructions, and are included in the verified open-system ranking reported here. Beyond the ranking, this report analyzes exposure subsets, semantically distinct test cases, a shared failure pattern, system design choices, and inference strategies. The top systems obtain closely spaced average scores, while the best-performing method varies across cases and metrics; under severe underexposure, all verified systems retain visible local errors.

Figures & tables

Figure 1 : Adapted from SEE-Net [ 15 ] . Brightness distributions and task settings of SDE [ 4 ] and SEE-600K [ 15 ] . (a) SDE covers a low-to-normal brightness range. (b) SEE-600K spans low-light, normal-light, and high-light conditions. (c) Earlier low-light methods map dark inputs to a fixed normal-light target. (d) The official SEE Challenge evaluation conditions restoration on a target-brightness statistic $B$ derived from the reference image.

Split	Scenes	Pairs	Reference	Purpose	Motion setting
Training split	165	509,132	Public	Training	Camera motion
Test split	37	147,368	Public	Phase 1 validation	Camera motion
Hidden final split	6	3,405	Hidden	Phase 2 validation	Camera and scene motion

Table 1 : Data used by the challenge. Pair counts refer to constructed source–target restoration pairs rather than distinct raw frames. The three splits are scene-disjoint.

(a) Phase 2 evaluation on Codabench
Participant	Average		Low-to-Normal		High-to-Normal		FLOPs (G)	Params (M)
Participant	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	FLOPs (G)	Params (M)
pixelartai	23.1810	0.7246	21.2066	0.6965	25.1555	0.7527	1314.77	10.24
vincent2013	23.0865	0.7178	21.1040	0.6941	25.0689	0.7416	3390.56	54.21
EventFuse	22.7992	0.7057	21.1942	0.6809	24.4042	0.7305	97.51	1.16
bucloud	22.6168	0.7048	20.7068	0.6779	24.5268	0.7316	870.37	15.85

Table 2 : Results of the SEE Challenge 2026 under Phase 2 Codabench and organizer-side dense sampling. Dense-sampling PSNR determines the ranking, while SSIM is secondary. Best and second-best results are shown in bold and underlined . FLOPs (G) and parameters are reported at the native resolution. FLOPs (G) include cascaded stages but exclude TTA, temporal averaging, ensembles, and post-processing.

	Robot Motion (G1)				Checkerboard (G2)				Chinese Text (G3)
Team	PSNR $\uparrow$	SSIM $\uparrow$	L1 $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	L1 $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	L1 $\downarrow$	LPIPS $\downarrow$
pixelartai	18.76	0.4998	0.0826	0.2767	21.49	0.7951	0.0638	0.1553	24.83	0.7486	0.0375	0.1838
vincent2013	18.85	0.5010	0.0805	0.2701	21.32	0.7941	0.0657	0.1548	25.06	0.7583	0.0364	0.1800
EventFuse	18.73	0.4889	0.0847	0.3100	21.80	0.7902	0.0622	0.1556	24.40	0.7498	0.0427	0.1877
bucloud	18.71	0.4956	0.0848	0.3069	21.17	0.7814	0.0668	0.1694	24.52	0.7484	0.0400	0.1777
jiangbin	18.79	0.4986	0.0852	0.3431	21.11	0.7603	0.0706	0.1748	23.69	0.7299	0.0467	0.2217

Table 3 : Performance comparison across different groups.

Figure 2 : Qualitative comparison of the verified submissions on representative Low-to-Normal and High-to-Normal examples. Input RGB frames, event visualizations, reference images, restored outputs, and enlarged difficult regions are displayed with a common image range and without additional gamma or contrast adjustment. The examples illustrate differences in residual noise, color, local contrast, and texture recovery that are not fully captured by average PSNR and SSIM.

Figure 3 : Representative shared failure case under severe underexposure. (a) Accumulated events, (b) input frame, (c) SEE-Net baseline, (d)–(e) and (g)–(j) verified submissions, and (f) ground-truth frame. The green boxes indicate the enlarged regions shown below. Although the submitted systems substantially brighten the input, none faithfully reconstructs the checkerboard structure. The values below each result denote PSNR/SSIM/LPIPS ( $\uparrow/\uparrow/\downarrow$ ).

Team	Pretraining	Prompt	TTA	Temporal Processing	Effective Passes
pixelartai	$\times$	$\checkmark$	$\times$	$\checkmark$	1
vincent2013	$\checkmark$	$\checkmark$	$\checkmark$	$\times$	16
EventFuse	$\times$	$\checkmark$	$\times$	$\times$	1
bucloud	$\times$	$\checkmark$	$\checkmark$	$\times$	4
jiangbin	$\checkmark$	$\checkmark$	$\times$	$\times$	1
aka18	$\times$	$\checkmark$	$\checkmark$	$\times$	4

Table 4 : Comparison of training and inference strategies adopted by the participating teams and the SEE baseline. All methods use the brightness prompt. Effective Passes denotes the number of model forward passes or iterative updates used during inference.

Team	Participants	Affiliation
MLSLabs (pixelartai)	Dongyang Zhang, Renjie Zou, Zhiwei Huang, Dong Jiang	Malanshan Audio & Video Laboratory
ACVLab-TL (vincent2013)	Yun-Tze Tsai, Shao-Kai Liu, Chia-Ming Lee, Chih-Chung Hsu	Advanced Computer Vision Lab (ACVLab), National Yang Ming Chiao Tung University
EventFuse	Yixin Chen, Lupeng Liu	University of Chinese Academy of Sciences
ACVLab-LCY (bucloud)	Chia-Yu Lin	Advanced Computer Vision Lab (ACVLab), National Yang Ming Chiao Tung University; National Cheng Kung University
VisionLab-JB (bin_jiang)	Bin Jiang	Nanjing University
aka18	Tao Liu	Wuhan University

Table 5 : Contributing teams, participant names, and affiliations for the verified systems summarized in this paper.

Explore similar work

BiasBench: A reproducible benchmark for tuning the biases of event cameras
Apr 25, 2025Andreas Ziegler, David Joseph, Thomas Gossard +2Camera Biases
Cognitive Systems Group, University of Tübingen, Germany
Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
May 21, 2026Senyan Xu, Zhijing Sun, Kean Liu +5Low-Light Image Enhancement High-Resolution
University of Science and Technology of China
EvLIR: Learning Illumination Residuals from Ordered Events for Low-Light Image Enhancement
Jun 28, 2026Haoxian Zhou, Chuanzhi Xu, Langyi Chen +5Low-Light Image Enhancement Low-Resolution
1The University of Sydney · 2Massachusetts Institute of Technology

Apr 25, 2025, cs.CVJ/K move · Enter open · S save

BiasBench: A reproducible benchmark for tuning the biases of event cameras

Andreas Ziegler, David Joseph, Thomas Gossard, Emil Moldovan+1

Cognitive Systems Group, University of Tübingen, Germany

Camera Biases Reproducibility Bio-Inspired Framework

Open paper AskPDF arXiv

Event-based cameras are bio-inspired sensors that detect light changes asynchronously for each pixel. They are increasingly used in fields like computer vision and robotics because of several advantages over traditional frame-based cameras, such as high temporal resolution, low latency, and high dynamic range. As with any camera, the output's quality depends on how well the camera's settings, called biases for event-based cameras, are configured. While frame-based cameras have advanced automatic configuration algorithms, there are very few such tools for tuning these biases. A systematic testing framework would require observing the same scene with different biases, which is tricky since event cameras only generate events when there is movement. Event simulators exist, but since biases heavily depend on the electrical circuit and the pixel design, available simulators are not well suited for bias tuning. To allow reproducibility, we present BiasBench, a novel event dataset containing multiple scenes with settings sampled in a grid-like pattern. We present three different scenes, each with a quality metric of the downstream application. Additionally, we present a novel, RL-based method to facilitate online bias adjustments.

Abstract

Explore similar work

BiasBench: A reproducible benchmark for tuning the biases of event cameras

Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset

EvLIR: Learning Illumination Residuals from Ordered Events for Low-Light Image Enhancement