Binarized High-Efficiency RAW Video Restoration and Beyond

Tianyu Zhu; Ying Fu; Hesong Li; Gengchen Zhang; Xin Yuan; Yulun Zhang

cs.CVAug 17, 2026

Binarized High-Efficiency RAW Video Restoration and Beyond

Authors: Tianyu Zhu, Ying Fu, Hesong Li, Gengchen Zhang, Xin Yuan, Yulun Zhang

Organizations: School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China · Chinese Aeronautical Establishment, Beijing, China · Westlake University, Hangzhou, China · MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China

Abstract

RAW video restoration is fundamental to high-quality low-level perception and serves as the basis for a wide range of downstream vision applications. While binary neural networks (BNNs) enable efficient lightweight deployment for image enhancement, their deficiencies in modeling temporal coherence and activation value distributions hinder their effectiveness when applied to video scenarios. In this paper, we propose BinRVR, a binarized RAW video restoration framework that reduces computation and parameters by approximately 96% while incurring only about 4% performance degradation. Specifically, we present a Binarized Information Interaction Module (BIIM) to jointly model spatial and temporal information in an efficient and unified manner. Moreover, we develop a Distribution-Aware Binarized Convolution (DAB-Conv) that leverages the statistics of full-precision activations to mitigate quantization errors. The proposed framework further supports multi-bit quantization, enabling flexible accuracy-efficiency trade-offs across different hardware constraints. Extensive experiments demonstrate that our BinRVR achieves competitive performance compared with state-of-the-art binarized methods on RAW video restoration tasks, including low-light enhancement, denoising, deblurring, and super-resolution. We further explore the potential of our method on downstream video applications, including object detection and monocular depth estimation.

Figures & tables

Fig. 1: Performance and model complexity comparison with state-of-the-art binary neural networks (BNNs) and lightweight full-precision methods in RAW video restoration. The size of each circle reflects the model’s parameter count. Our method outperforms both the BNN-based methods and lightweight full-precision methods with comparable model complexity.

Fig. 2: Illustration of the proposed BinRVR. (a) Overall architecture of our binarized RAW video restoration framework. The recurrent arrows indicate the propagated features between adjacent sliding windows. Efficient inter-frame and intra-frame information interaction under binarization is achieved by the proposed Binarized Information Interaction Module (BIIM), whose detailed structure is shown in Fig. 3 . (b) Distribution-Aware Binarized Convolution (DAB-Conv), which leverages feature distribution information to reduce quantization error and improve representation capability in binarized networks.

Fig. 3: Detailed illustration of the proposed Binarized Information Interaction Module (BIIM). It is designed to enable efficient interaction between inter-frame temporal information and intra-frame spatial information under binarization through lightweight operations. (a) Binarized Information Interaction Encoder. (b) Binarized Information Interaction Decoder.

Fig. 4: Comparison of video restoration architectures. (a) Multi-frame sliding window framework. (b) Single-frame recurrent architecture. (c) Proposed sliding window recurrent connection.

Fig. 5: Illustration of spatial information interaction module. (a) Illustration of the spatial information interaction module, where feature channels are split into identity, $3\times 3$ , $1\times 11$ , and $11\times 1$ binarized depthwise convolution branches. (b) FLOPs per spatial location versus kernel size. (c) Parameter complexity versus kernel size.

Method	Params (M) $\downarrow$	FLOPs (G) $\downarrow$	SMOID [ 37 ]									LLRVD [ 10 ]
			Gain0			Gain15			Gain30			LLRVD [ 10 ]
			PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$
Linear Scaled	-	-	31.26	0.7665	0.4965	32.35	0.8108	0.2541	32.27	0.8358	0.4156	30.04	0.6941	0.0863
Full-precision methods
SMOID [ 37 ]	12.21	15.11	39.74	0.9733	0.0446	39.43	0.9751	0.0461	40.06	0.9769	0.0431	37.07	0.9580	0.0391
RViDeNet [ 38 ]	8.57	65.77	41.09	0.9778	0.0510	40.94	0.9803	0.0494	41.60	0.9818	0.0500	37.39	0.9620	0.0400

TABLE I: Quantitative comparison on SMOID [ 37 ] and LLRVD [ 10 ] for low-light RAW video enhancement. For binarized methods, the best and second-best results are shown in bold and underlined , respectively. Lightweight full-precision methods are additionally included for reference, with the best result shown in bold .

Fig. 6: Visual comparisons of binarized methods on the SMOID [ 37 ] and LLRVD [ 10 ] datasets for low-light RAW video enhancement (left: SMOID; right: LLRVD). For each example, the left half shows zoomed-in RGB results obtained by applying an ISP pipeline to the RAW outputs, while the right half presents the corresponding error maps with respect to the ground truth.

Method	Noisy	FastDVD [ 40 ]	EMVD-S [ 42 ]	RViDeNet [ 38 ]	LLRVD [ 10 ]	FloRNN [ 13 ]	BNN [ 19 ]	Bireal [ 61 ]	IRNet [ 62 ]	ReActNet [ 59 ]	BTM [ 69 ]	BBCU [ 20 ]	BiSRNet [ 84 ]	FRBC [ 85 ]	BHViT [ 72 ]	BinRVR (Ours)
Params(M) $\downarrow$	-	2.48	0.81	8.57	6.29	10.49	0.26	0.26	0.26	0.28	0.25	0.27	0.28	0.26	0.27	0.22
FLOPs(G) $\downarrow$	-	10.50	1.66	65.77	46.14	24.57	1.38	1.38	1.38	1.56	1.33	1.47	1.44	1.38	1.47	1.23
PSNR $\uparrow$	32.02	39.84	42.63	43.97	44.23	45.15	42.05	42.06	41.97	41.92	43.11	43.21	43.16	41.48	43.17	43.53
SSIM $\uparrow$	0.7333	0.9703	0.9851	0.9874	0.9879	0.9907	0.9804	0.9809	0.9800	0.9805	0.9847	0.9850	0.9848	0.9779	0.9849	0.9868
ST-RRED $\downarrow$	0.0171	-	-	-	-	-	0.0118	0.0109	0.0119	0.0116	0.0103	0.0100	0.0100	0.0119	0.0100	0.0080

TABLE II: Quantitative comparison on CRVD [ 53 ] for RAW video denoising. For binarized methods, the best and second-best results are shown in bold and underlined , respectively. Lightweight full-precision methods are additionally included for reference, with the best result shown in bold . The results of full-precision methods are reported from the original papers.

Fig. 7: Visual comparisons of binarized methods on the CRVD [ 53 ] dataset for RAW video denoising. For each example, the left half shows zoomed-in RGB results obtained by applying an ISP pipeline to the RAW outputs, while the right half presents the corresponding error maps with respect to the ground truth.

Method	Blurry	MIMO [ 91 ]	ESTRNN [ 92 ]	LIEDNet [ 93 ]	BNN [ 19 ]	Bireal [ 61 ]	IRNet [ 62 ]	ReActNet [ 59 ]	BTM [ 69 ]	BBCU [ 20 ]	BiSRNet [ 84 ]	FRBC [ 85 ]	BHViT [ 72 ]	BinRVR (Ours)
Params(M)	-	6.81	2.53	4.76	0.26	0.26	0.26	0.28	0.25	0.27	0.28	0.26	0.27	0.22
FLOPs(G)	-	16.00	12.77	5.09	1.38	1.38	1.38	1.56	1.33	1.47	1.44	1.38	1.47	1.23
PSNR $\uparrow$	36.52	38.15	38.12	38.61	36.88	36.81	36.95	37.33	37.35	37.50	37.71	36.88	37.33	38.89
SSIM $\uparrow$	0.9493	0.9663	0.9673	0.9708	0.9531	0.9520	0.9546	0.9583	0.9589	0.9607	0.9626	0.9548	0.9587	0.9724
ST-RRED $\downarrow$	0.0180	0.0151	0.0157	0.0098	0.0180	0.0158	0.0179	0.0169	0.0179	0.0175	0.0167	0.0168	0.0169	0.0106

TABLE III: Quantitative comparison on Deblur-RAW [ 90 ] for RAW video deblurring. For binarized methods, the best and second-best results are shown in bold and underlined , respectively. Lightweight full-precision methods are additionally included for reference, with the best result shown in bold .

Fig. 8: Visual comparisons of binarized methods on the Deblur-RAW [ 90 ] dataset for RAW video deblurring.

Method	Params (M) $\downarrow$	FLOPs (G) $\downarrow$	$2\times$			$3\times$			$4\times$
Method	Params (M) $\downarrow$	FLOPs (G) $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$
Bicubic	-	-	35.23	0.9434	0.2702	33.40	0.9121	0.2827	31.25	0.8558	0.7312
Full-precision methods
TDAN [ 95 ]	1.86	13.76	34.19	0.9344	0.4757	33.06	0.9203	0.5424	32.13	0.8882	0.9604
BasicVSR++ [ 29 ]	7.18	113.13	35.71	0.9579	0.3684	35.42	0.9345	0.3096	33.91	0.9121	0.5131
Realviformer [ 94 ] †	5.82	40.46	37.53	0.9729	0.1720	-	-	-	34.57	0.9305	0.3654

TABLE IV: Quantitative comparison on Real-RawVSR [ 9 ] for RAW video super-resolution. For binarized methods, the best and second-best results are shown in bold and underlined , respectively. Lightweight full-precision methods are additionally included for reference, with the best result shown in bold . Params and FLOPs are computed under the

2\times

scaling setting.

{\dagger}

indicates that Realviformer [ 94 ] and FRBC [ 85 ] fail to train at certain scales.

Fig. 9: Visual comparisons of binarized methods on Real-RawVSR [ 9 ] for RAW video super-resolution (top: $2\times$ ; bottom: $3\times$ ). For each example, the left half shows zoomed-in RGB results obtained by applying an ISP pipeline to the RAW outputs, while the right half presents the corresponding error maps with respect to the ground truth.

Tasks	Metrics	Linear Scaled	BNN [ 19 ]	Bireal [ 61 ]	IRNet [ 62 ]	ReActNet [ 59 ]	BTM [ 69 ]	BBCU [ 20 ]	BiSRNet [ 84 ]	FRBC [ 85 ]	BHViT [ 72 ]	BRVE [ 86 ]	BinRVR (Ours)
Object Detection	AP $\uparrow$	61.98	62.85	65.02	63.49	65.46	66.83	66.61	66.60	53.39	66.97	68.52	70.62
	AP 50 $\uparrow$	64.93	65.63	67.91	66.29	68.15	69.77	69.44	69.59	56.31	69.84	71.05	73.24
	AP 75 $\uparrow$	63.34	64.22	66.67	64.98	66.96	68.49	68.27	68.27	54.67	68.66	69.97	72.11
Depth Estimation	RMSE $\downarrow$	0.1308	0.1251	0.1270	0.1255	0.1224	0.1136	0.1115	0.1149	0.2215	0.1127	0.1067	0.1029
Depth Estimation	SSIM $\uparrow$	0.9324	0.9335	0.9313	0.9323	0.9342	0.9382	0.9392	0.9372	0.8770	0.9386	0.9463	0.9482

TABLE V: Quantitative results of downstream applications of low-light RAW video enhancement using the SMOID [ 37 ] dataset. We provide results for object detection and depth estimation. The best and second-best values are Bold and Underline , respectively.

Method	Bits (w/a)	Params $\downarrow$	FLOPs $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$
LSQ [ 18 ]	4/4	0.80M	5.81G	37.10	0.9585	0.0461
QuantSR [ 73 ]	4/4	0.80M	5.81G	37.09	0.9585	0.0460
Q-SCI [ 96 ]	4/4	0.80M	5.81G	37.13	0.9590	0.0433
Ours	4/4	0.80M	5.81G	37.71	0.9646	0.0382
LSQ [ 18 ]	3/3	0.63M	3.39G	37.05	0.9580	0.0465
QuantSR [ 73 ]	3/3	0.63M	3.39G	37.06	0.9581	0.0464

TABLE VI: Multi-Bit quantization results on LLRVD [ 10 ] dataset for low-light RAW video enhancement.

Fig. 10: Qualitative comparisons of object detection results produced by GroundingDINO [ 97 ] on enhanced videos.

Fig. 11: Qualitative comparisons of monocular depth estimation results produced by Depth Anything V2 [ 100 ] on enhanced videos.

Fig. 12: Effect of the sliding window stride on recurrent propagation. A larger stride improves efficiency but compromises temporal consistency in restored videos across frames.

Method	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$
RAW2RAW+ISP	30.59	0.8408	0.2002
RAW2RGB	27.53	0.8143	0.2938
RGB2RGB	24.91	0.7994	0.5941
RAW2RAW+ISP+H264	30.24	0.8421	0.1810
RGB2RGB+H264	24.88	0.8170	0.5610
H264+RGB2RGB	20.15	0.6138	1.4199

TABLE VII: Comparison of different low-light video enhancement settings on LLRVD [ 10 ] dataset. Metrics are computed in the RGB domain after ISP processing.

Arch.	Window	Rec.	Params $\downarrow$	FLOPs $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$
Pure sliding window	3	✗	0.22M	0.74G	36.83	0.9567	0.0648
Pure recurrent	1	✓	0.22M	1.05G	36.98	0.9579	0.0506
Hybrid (Ours)	3	✓	0.22M	1.23G	37.21	0.9599	0.0436

TABLE VIII: Architecture-level ablation study on the temporal modeling paradigm. All variants use the same backbone, 1-bit quantization setting, and training configuration.

Partition	Ablation	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	Params $\downarrow$	FLOPs $\downarrow$
BIIM Encoder	w/o TII	37.06	0.9585	0.0468	0.22M	1.23G
BIIM Encoder	Same as Decoder-TII	37.15	0.9586	0.0450	0.24M	1.43G
BIIM Decoder	w/o TII	37.00	0.9581	0.0470	0.21M	1.12G
	Same as Encoder-TII	37.14	0.9595	0.0451	0.21M	1.12G
	w/o SII	37.04	0.9580	0.0469	0.21M	1.17G
	Strip Kernel $\to 1\times 9$	37.16	0.9592	0.0453	0.22M	1.23G

TABLE IX: Ablation studies on our Binarized Information Interaction (BIIM) Module .

Sequence Length	Avg. over Gain0 / Gain15 / Gain30
Sequence Length	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$
30 frames	40.86	0.9789	0.0610
60 frames	40.88	0.9790	0.0606
90 frames	40.88	0.9790	0.0606
120 frames	40.88	0.9790	0.0605

TABLE X: Long-sequence evaluation on the SMOID [ 37 ] test set. The metrics are averaged over Gain0, Gain15, and Gain30, and computed on the same target interval.

$\text{Mean}(\cdot)$	$\text{Std}(\cdot)$	$\text{Mean}(\|\cdot\|)$	PSNR $\uparrow$	SSIM $\uparrow$	ST-RRED $\downarrow$	Params $\downarrow$	FLOPs $\downarrow$
✗	✗	✗	37.04	0.9581	0.0458	0.222M	1.21G
✓	✗	✗	37.12	0.9589	0.0447	0.222M	1.21G
✓	✓	✗	37.17	0.9595	0.0444	0.223M	1.21G
✓	✓	✓	37.21	0.9599	0.0436	0.223M	1.23G

TABLE XI: Ablation studies for our Distribution-Aware Binarized Convolution.

Fig. 13: Visual ablation comparison of representative BinRVR variants. (a) Ablation of temporal modeling components. (b) Ablation of spatial modeling components. Each comparison includes the degraded input, ablation variants without key components, the full model, the ground truth, and the corresponding error maps.

Fig. 14: Visualization of activation distributions and DAB-Conv scaling factors. (a)–(c) Channel-wise activation statistics before binarization under different gain settings. (d)–(f) Representative activation distributions from different channels. (g)–(i) Predicted DAB-Conv scales versus activation statistics. The results show that activation distributions vary across channels and degradations, motivating input-dependent channel-wise scaling.

Platform	Model	Mode	FPS $\uparrow$	Latency (ms/f.) $\downarrow$	PSNR $\uparrow$
NVIDIA RTX 4060 GPU Local laptop	ShiftNet	FP32	3.74	267.34	37.87
NVIDIA RTX 4060 GPU Local laptop	Ours	FP32	93.22	10.73	37.81
NVIDIA Ampere GPU NVIDIA Jetson Orin NX	ShiftNet	FP32	1.30	770.39	37.87
	Ours	FP32	19.94	50.16	37.81
	Ours	W8A8	35.18	28.42	37.77
Intel Core Ultra 9 CPU Local laptop	ShiftNet	FP32	0.87	1144.17	37.87

TABLE XII: Actual-runtime deployment comparison with the representative full-precision method ShiftNet [ 8 ] on different hardware platforms under currently supported inference modes. PSNR is evaluated on the LLRVD [ 10 ] test set.

Video Restoration

Video restoration reconstructs clearer, more faithful, temporally consistent footage from blur, noise, compression, weather, and other degradations.

See all 59 papers

EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion
Jul 7, 2026Onur Eker, Erkut Erdem, Aykut ErdemLow-Light Image Enhancement Multimodal Sensor Fusion
Department of Computer Engineering, Hacettepe University, TR-06800 Ankara, Turkey, and also with HAVELSAN Inc., TR-06510, Ankara, Turkey · Department of Computer Engineering, Hacettepe University, TR-06800 Ankara, Turkey, and also with the Koc University Is Bank AI Center, TR-34450, Istanbul, Turkey · Department of Computer Engineering, Koc University, TR-34450 Istanbul, Turkey, and also with the Koc University Is Bank AI Center, TR-34450, Istanbul, Turkey
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion
Sep 29, 2026Xiaoxu Chen, Qin Yang, Haoran Bai +2Diffusion Transformer Video Restoration
Alibaba Group · Xidian University
RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression
Mar 30, 2026Chunhang Zheng, Tongda Xu, Mingli Xie +2Learned Image Compression
School of Electronics, Peking University, Beijing, 100871, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, 100084, China · the University of Chinese Academy of Sciences, Beijing, 100190, China

Jul 7, 2026J/K move · Enter open · S save

EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion

Onur Eker, Erkut Erdem, Aykut Erdem

Department of Computer Engineering, Hacettepe University, TR-06800 Ankara, Turkey, and also with HAVELSAN Inc., TR-06510, Ankara, Turkey · Department of Computer Engineering, Hacettepe University, TR-06800 Ankara, Turkey, and also with the Koc University Is Bank AI Center, TR-34450, Istanbul, Turkey · Department of Computer Engineering, Koc University, TR-34450 Istanbul, Turkey, and also with the Koc University Is Bank AI Center, TR-34450, Istanbul, Turkey

Low-Light Image Enhancement Multimodal Sensor Fusion

Open paper AskPDF arXiv

Enhancing videos under extreme low-light conditions remains challenging due to the difficulty of balancing restoration quality and computational efficiency in resource-constrained settings. This paper introduces EeveeDark, a low-light video enhancement framework that combines the spatial richness of sensor-level RAW data with the temporal precision of event streams. Central to our model is a Binary Neural Network (BNN) architecture that reduces computational overhead by quantizing weights and activations while preserving detail. EeveeDark incorporates (i) modality-specific binary encoders for processing RAW frames and event data, (ii) a lightweight fusion block for integrating spatial and temporal cues, and (iii) an event-guided skip gating mechanism for dynamic spatiotemporal refinement. Experiments on synthetic and real-world datasets show that EeveeDark outperforms prior BNN-based methods and offers a favorable performance-efficiency trade-off compared to full-precision models. The project page is available at https://cyberiada.github.io/EeveeDark.

Abstract

Video Restoration

Explore similar work

EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion

FastVR: Efficient Streaming Video Restoration with One-Step Diffusion

RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression