OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation

Yini Li; Joanne Lin; David Blackham; David Bull; Nantheera Anantrasirichai

cs.CVOct 14, 2026

OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation

Authors: Yini Li, Joanne Lin, David Blackham, David Bull, Nantheera Anantrasirichai

Organizations: Visual Information Laboratory, University of Bristol, Bristol, United Kingdom

Abstract

Low-light video processing remains an underexplored problem in computer vision, primarily due to the scarcity of high-quality ground-truth data. Existing public datasets exhibit several limitations, including restricted motion diversity, limited scene coverage, weak degradations, reliance on auxiliary modalities such as event data, and misalignment between low-light inputs and ground truth. Furthermore, current datasets typically address either low-light enhancement or scene understanding, whereas these tasks should be considered jointly. We introduce OLiVES, a benchmark dataset for outdoor low-light videos with dynamic scenes, designed to support both low-light video enhancement (LLVE) and video object segmentation (VOS). The dataset addresses key content gaps by incorporating a diverse range of natural textures, animals, occlusions, dynamic activities, and close-up scenes. To the best of our knowledge, OLiVES is the first outdoor low-light video dataset captured using professional cinema-grade cameras. It provides over 25,000 aligned normal- and low-light frame pairs, along with over 46,000 VOS annotations. We benchmark state-of-the-art LLVE and VOS methods on OLiVES and show that training on it improves performance on both tasks. The OLiVES project page is available at: https://anonymous-OLiVES.github.io/.

Figures & tables

Figure 1: Examples of the OLiVES dataset. (a) Low-light videos with their corresponding normal-light ground truth and object segmentation masks. Each scene is provided at multiple light levels, (b) illustrating the noise levels exhibited in the low-light videos when using different ND filters (histogram-matched to GT for comparison).

Dataset	Modality	Frames	Cam. Motion	Obj. Motion	Resolution	VOS ann.	Device
DRV [ 3 ]	Raw	22,220	Static	Static	$5496\times 3672$	✗	Sony RX100 VI
SDSD [ 40 ]	RGB	37,500	Dynamic	Static	$1920\times 1080$	✗	Canon 6D Mark II
LLRVD [ 14 ]	Raw	4,086	Dynamic	Dynamic	$2600\times 1400$	✗	Sony $\alpha$ 7R IV
BVI-RLV [ 31 ]	RGB	31,800	Dynamic	Static	$1920\times 1080$	✗	Sony $\alpha$ 7S II
SDE [ 4 ]	RGB/Event	31,477	Dynamic	Static	$346\times 260$	✗	DAVIS 346
DID [ 13 ]	RGB	41,038	Dynamic	Static	$2560\times 1440$	✗	5 Camera Models

Table 1: Comparison of low-light video enhancement datasets.

Dataset	Light	Frames	Categories	Objects	Annotations	New objects
DAVIS 2016 [ 35 ]	Normal	3,440	-	50	3,455	✗
DAVIS 2017 [ 36 ]	Normal	6,208	-	205	13,543	✗
YouTube-VOS [ 42 ]	Normal	120,532	94	7755	197,272	✓
MOSEv1 [ 10 ]	Normal	130,149	36	5,200	431,725	✗
MOSEv2 [ 11 ]	Mixed	468,251	200	10,074	701,976	✗
LLE-VOS [ 23 ]	Low	5,600	-	120	9,606	✗

Table 2: Comparison of video object segmentation (VOS) datasets.

Figure 2: Capture setup. (a) Our beam-splitter rig with two genlocked cinema cameras mounted on a shared tripod. (b) Schematic of the optical path: incoming light is split between Camera 1, which records the normal-light ground truth $I_{gt}$ , and Camera 2, which records the low-light frame $I_{low}$ through one of three ND filters (1/16, 1/32, 1/64). Genlock ensures temporal synchronization between the two streams.

Figure 3: Registration pipeline of the OLiVES dataset.

Figure 4: Finetuning the fine feature encoder of RoMa with synthetically degraded low-light pairs and a contrastive objective to improve robustness to low-light degradations.

Figure 5: Dataset statistics overview. (a) Normalized pixel intensities for normal/low-light pairs, (b) ND filter ratios, (c) optical flow of VOS, (d) noise level distributions, (e) object category and size distributions.

Split	Videos	Frames	Objects	Anns.
Train	129	8,826	275	17,901
Validation	99	7,012	196	12,820
Test	102	7,055	245	15,646

Table 3: Summary of OLiVES VOS benchmark for the train, validation and test set.

Method	Venue	Type	Data	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	tLPIPS $\downarrow$ $\times 10^{-2}$	WE $\downarrow$ $\times 10^{-2}$	VMAF $\uparrow$
SNR-aware [ 43 ]	CVPR’22	S	I	26.20	0.835	0.268	6.47	5.97	73.51
LLFlow [ 41 ]	AAAI’22	S	I	21.65	0.862	0.219	2.82	3.81	69.50
Retinexformer [ 2 ]	ICCV’23	S	I	27.65	0.834	0.241	6.35	5.41	76.93
LightenDiffusion [ 21 ]	ECCV’24	UP	I	20.32	0.741	0.380	8.70	5.56	54.36
Wakeup-darkness [ 51 ]	ACM TOMM’25	US	I	17.46	0.534	0.630	8.82	9.26	71.39
SGZSL [ 52 ]	WACV’22	US	V	16.61	0.527	0.693	10.70	11.80	74.74

Table 4: Benchmarking on OLiVES dataset across recent LLVE and LLIE SOTA methods. Bold and underline denote the best and second-best performances among all methods respectively.

Method	Venue	OLiVES val				OLiVES test				LLE-VOS [ 23 ] val
Method	Venue	$\mathcal{J}\&\mathcal{F}$	$\mathcal{J}$	$\mathcal{F}$	$\mathcal{B}$	$\mathcal{J}\&\mathcal{F}$	$\mathcal{J}$	$\mathcal{F}$	$\mathcal{B}$	$\mathcal{J}\&\mathcal{F}$	$\mathcal{J}$	$\mathcal{F}$
STCN [ 8 ]	NeurIPS’21	89.4	87.2	91.5	83.5	78.3	73.8	82.9	70.8	32.3	37.9	26.7
AOT [ 47 ]	NeurIPS’21	91.5	88.5	94.6	85.1	80.5	75.8	85.1	73.4	54.1	57.5	50.7
De-AOT [ 48 ]	NeurIPS’22	91.5	88.4	94.5	85.0	86.9	82.0	91.7	80.0	62.6	65.6	59.7
XMem [ 7 ]	ECCV’22	86.9	84.4	89.5	79.5	74.4	68.9	79.8	65.3	53.0	56.0	50.1
Cutie [ 6 ]	CVPR’24	93.1	91.3	94.8	88.0	88.3	84.2	92.4	82.0	59.2	62.8	55.7

Table 5: Benchmark of SOTA VOS methods trained on the OLiVES dataset and evaluated on OLiVES validation and test set, and LLE-VOS validation set. Bold and underline denote the best and second-best performances among all methods respectively.

LLVE Method	LLE-VOS [ 23 ] val
LLVE Method	$\mathcal{J}\&\mathcal{F}$	$\mathcal{J}$	$\mathcal{F}$
Cutie (off-the-shelf) [ 6 ]	53.2	58.5	48.0
LLVE-STCD [ 45 ] + Cutie	57.9	62.1	53.8
BVI-Mamba [ 20 ] + Cutie	58.1	62.0	53.8
RetinexFormer [ 2 ] + Cutie	58.3	61.9	54.6

Table 6: Quantitative results of two-stage methods on LLE-VOS validation set, using LLVE methods trained on OLiVES and pre-trained Cutie [ 6 ] .

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Method	AUC@5	AUC@10	AUC@20
Pretrained	62.28	76.45	86.25
Replace Coarse Features	62.19	76.35	86.15
Replace Fine Features	52.33	68.68	80.79

Appendix

Table 7: Ablation study on the impact of coarse and fine features in RoMa. We replace the corresponding features in the pretrained model with those extracted from degraded inputs.

Method	Non-degraded			Degraded
Method	AUC@5	AUC@10	AUC@20	AUC@5	AUC@10	AUC@20
Pretrained	62.28	76.45	86.25	54.75	70.42	82.04
I: Deg. Aug.	+0.34	+0.11	+0.04	+2.43	+2.06	+1.46
II: I+VICReg	+0.10	-0.03	-0.06	+2.74	+2.17	+1.49
III: II+InfoNCE	+0.56	+0.38	+0.17	+3.12	+2.44	+1.66

Appendix

Table 8: Finetuning performance of RoMa on non-degraded and degraded MegaDepth-1500. All values (except the first row) indicate absolute improvements over the pretrained baseline.

Figure 6: Qualitative results of LLVE methods trained on OLiVES.

Figure 7: Custom annotation software to create manual annotations for OLiVES VOS benchmark.

Figure 8: Qualitative comparison of Cutie on an example video from MOSEv2 [ 11 ] (reduced frame brightness for better segmentation visibility). (Left) the first frame with the input masks. (Right) Crops of segmentation outputs for Cutie [ 6 ] with various training data.

Size	Count	OLiVES test
Size	Count	$\mathcal{J}\&\mathcal{F}$	$\mathcal{J}$	$\mathcal{F}$
Small	5	-	-	-
Medium	40	-	-	-
Large	109	-	-	-

Appendix

Table 9: Quantitative results on OLiVES test set, grouped by size of the objects. Count is the total count of the object sizes.

Figure 9: Examples of difficult segmentation scenarios in OLiVES.

Explore similar work

ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark
Dec 1, 2025Joanne Lin, Ruirui Lin, Yini Li +2Instance Segmentation Video Object Segmentation
Visual Information Laboratory, University of Bristol
Reading in the Dark: Low-light Scene Text Recognition
Apr 26, 2026Xuanshuo Fu, Lei Kang, Ernest Valveny +2Scene Text Recognition Low-Light Image Enhancement
Computer Vision Center, Barcelona, Spain
NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge
Aug 10, 2026Aleksei Khalin, Egor Ershov, Artyom Panshin +46Image Enhancement Low-Light Image Enhancement

Dec 1, 2025J/K move · Enter open · S save

ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark

Joanne Lin, Ruirui Lin, Yini Li, David Bull+1

Visual Information Laboratory, University of Bristol

Instance Segmentation Video Object Segmentation Domain Adaptation Low-Light Image Enhancement

Open paper AskPDF arXiv

Video instance segmentation (VIS) for low-light content remains highly challenging for both humans and machines alike, due to noise, blur and other adverse conditions. The lack of large-scale annotated datasets and the limitations of current synthetic pipelines, particularly in modeling temporal degradations, further hinder progress. Moreover, existing VIS methods are not robust to the degradations found in low-light videos and, consequently, perform poorly even after finetuning. In this paper, we introduce ELVIS (Enhance Low-Light for Video Instance Segmentation), a framework that enables domain adaptation of state-of-the-art VIS models to low-light scenarios. ELVIS is comprised of an unsupervised synthetic low-light video pipeline that models both spatial and temporal degradations, a calibration-free degradation profile estimation network (VDP-Net) and an enhancement decoder head that disentangles degradations from content features. ELVIS improves performances by up to +3.7AP on the synthetic low-light YouTube-VIS 2019 dataset and beats two-stage baselines by at least +2.8AP on real low-light videos. Code and dataset available at: https://joannelin168.github.io/research/ELVIS

Abstract

Explore similar work

ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark

Reading in the Dark: Low-light Scene Text Recognition

NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge