Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators

Yu Wang; Shaohua Wang; Yicheng Li; Kecheng Sun

cs.CVOct 29, 2026

Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators

Authors: Yu Wang, Shaohua Wang, Yicheng Li, Kecheng Sun

Organizations: Institute of Automotive Research, Jiangsu University, Zhenjiang 212013, China

Abstract

Intermediate-fusion cooperative perception lets a vehicle detect objects beyond its own field of view by fusing features shared by nearby agents. When only a collaborator's cameras are degraded by fog, motion blur or exposure errors, the features it shares drift away from the training distribution while the ego input stays clean, and cooperation can become worse than not cooperating at all. Test-time batch-normalization adaptation, the standard training-free remedy, estimates statistics over the pooled batch of all agents and therefore normalizes both the clean ego and the corrupted collaborator with a mixture of two distributions. We show that this mixing harms even the clean ego: when the ego shares BN statistics with a corrupted collaborator, its detection from its own features drops by 3.58 to 6.68 [email protected] points although its cameras are untouched. We propose AgentNorm, an agent-wise test-time normalization that i) estimates the normalization statistics of every collaborator from its own current observation and ii) anchors the ego to its source statistics, so that the ego path remains exactly the original model. AgentNorm has no learnable parameters, needs no gradients or labels, is independent of the order of test frames, and runs locally on each agent without changing the transmitted features. On camera-based OPV2V with four fusion checkpoints and collaborator-only corruptions, AgentNorm raises [email protected] under severity-5 fog from 29.42-37.25 to 43.32-58.86 and outperforms pooled normalization by 5.53-12.94 points under fog and motion blur, at an extra latency of 2.3 ms per frame. On the real-world DAIR-V2X-C dataset, it outperforms pooled normalization in all ten infrastructure-corruption settings. We also report the cases it does not fix: occlusion, which removes image content rather than shifting feature statistics, and the case in which all agents share the same shift.

Figures & tables

Setting	Source data	Target labels	Re- training	Test-time gradients	Agent- specific shift
Fine-tuning	–	✓	✓	–	–
Domain adaptation	✓	–	✓	–	–
Domain generalization	✓	–	✓	–	–
Test-time training	✓	–	✓	✓	–
Fully TTA (e.g., Tent)	–	–	–	✓	–
Test-time BN	–	–	–	–	–

TABLE I: Adaptation settings. Our setting keeps the constraints of test-time BN and adds that the shift may affect only a subset of the agents processed by the same network.

Fig. 1: Statistics of the collaborator’s BEV features versus the severity of its camera corruption (AttFuse, OPV2V test, ego clean). (a) Mean normalized distance to the source statistics. (b) Mean local variance. Both change monotonically for all corruption types.

Corruption	Sev.	AUROC	No adapt.	Ego only	Score gating	Random gating	Oracle gating
Fog	3	0.719	38.85	38.31	39.09	39.50	41.16
Fog	5	0.743	37.25	38.31	38.45	38.80	40.02
Motion blur	3	0.708	42.53	38.31	40.36	42.06	44.16
Motion blur	5	0.752	36.48	38.31	38.14	38.25	39.91
Brightness	3	0.650	53.00	38.31	44.35	50.78	51.78
Brightness	5	0.719	42.37	38.31	41.01	41.69	42.28

TABLE II: Region-level gating of the collaborator (AttFuse, OPV2V, [email protected]). Only the collaborators’ cameras are corrupted. AUROC: localization of shifted cells by the gating score. Gating columns report the best of

k\in\{10,30,50\}\%

. Underlined: cooperation below ego-only. Oracle uses the paired clean frame and is not a feasible method.

Panel of Figure 4 — Fig. 2: One BN layer of the per-agent encoder with a clean ego ( $X_{0}$ , blue) and a corrupted collaborator ( $X_{1}$ , orange). (a) Pooled test-time BN normalizes both agents with the mixture statistics $(\boldsymbol{\mu}_{P},\boldsymbol{\sigma}_{P}^{2})$ , which shifts the clean ego (dashed) and under-corrects the collaborator. (b) AgentNorm keeps the ego on the source statistics (ego anchoring) and normalizes the collaborator with the statistics of its own current observation (agent-wise statistics).

Fig. 3: Mechanism analysis on AttFuse (OPV2V, severity 5). (a) AP@0.5 of the clean ego detected from its own feature alone, under source statistics, its own statistics, and statistics pooled with a clean or corrupted collaborator. Pooling with a corrupted collaborator lowers the ego’s own detection by 3.58–6.68 points. (b) AP@0.5 of cooperative detection when agent-wise statistics are applied only in the BEV backbone, only in the image encoder, or in both (AgentNorm). — Fig. 3: Mechanism analysis on AttFuse (OPV2V, severity 5). (a) [email protected] of the clean ego detected from its own feature alone, under source statistics, its own statistics, and statistics pooled with a clean or corrupted collaborator. Pooling with a corrupted collaborator lowers the ego’s own detection by 3.58–6.68 points. (b) [email protected] of cooperative detection when agent-wise statistics are applied only in the BEV backbone, only in the image encoder, or in both (AgentNorm).

Fig. 4: BEV features on an OPV2V test frame (AttFuse) with the collaborator under severity-5 fog and a clean ego. (a)–(c) Channel-averaged magnitude of the collaborator’s feature with clean cameras, with fog, and with fog after AgentNorm. (d) Channel-averaged absolute change of the ego’s feature relative to the source model under Pooled BN. Under AgentNorm the same change averages $7.3\times 10^{-5}$ (floating-point level, against 0.016 for Pooled BN) because the ego keeps its source statistics, so it is not plotted.

Fig. 5: One collaborator camera image of OPV2V under the four corruptions at severity 5. Only the collaborators’ cameras are corrupted; the ego’s cameras stay clean.

		[email protected]				[email protected]
Model	Corruption	No adapt.	Pooled BN	Ours	$\Delta$	No adapt.	Pooled BN	Ours
AttFuse	Fog	37.25	40.65	51.98	+11.34	19.04	18.08	24.35
	Motion blur	36.48	42.90	49.83	+6.93	18.59	18.94	22.88
	Brightness	42.37	53.87	55.59	+1.72	21.46	23.47	25.70
	Occlusion	39.92	35.17	35.63	+0.46	19.87	14.83	17.95
V2X-ViT	Fog	29.69	45.92	58.86	+12.94	13.14	20.16	27.98

TABLE III: Collaborator-only corruption at severity 5 on OPV2V (camera). [email protected] and [email protected] in %.

\Delta

: AgentNorm minus Pooled BN in [email protected] points. Best per row in bold.

Fig. 6: [email protected] of AttFuse on OPV2V as the severity of the collaborator’s corruption increases (ego clean). The dotted line is the ego-only model. Under fog and motion blur, AgentNorm degrades much more slowly than Pooled BN and stays above the ego-only model; under occlusion, no method helps.

	Severity 3			Severity 5
Corruption	None	Pooled	Ours	None	Pooled	Ours
Fog	1.65	2.78	6.75	1.50	2.07	5.88
Snow	1.57	4.82	7.35	1.16	2.44	5.17
Frost	1.41	3.42	6.00	1.30	2.71	5.40
Brightness	5.61	7.25	8.82	1.17	3.79	6.08
Motion blur	8.97	7.55	8.93	6.86	6.01	7.46

TABLE IV: Roadside-only corruption on DAIR-V2X-C (camera CoAlign, [email protected] in %). For each severity: no adaptation / Pooled BN / AgentNorm. Best per severity in bold. The vehicle-only model reaches 1.65.

Fig. 7: Remedies for a corrupted collaborator (AttFuse, OPV2V, collaborator fog at severity 5). The dashed line marks no adaptation. The oracle uses ground-truth labels and is shown only as a reference.

Fig. 8: Detections on an OPV2V test frame (AttFuse) with two collaborators (orange triangles) under severity-5 fog and a clean ego (black triangle). From left to right: no adaptation, Pooled BN and AgentNorm. Solid green boxes: ground truth; dashed boxes: predictions. Gray points are the LiDAR scan provided by OPV2V, drawn only to show the road layout and the agents’ surroundings; no model in this paper uses LiDAR. True positives at IoU 0.5: 6, 8 and 13 of 21 objects. The frame was selected as the one with the largest gain of AgentNorm over no adaptation among 115 candidate frames (every 18th test frame); statistics over all candidates are given in the text.

Variant	Fog	Motion blur	Brightness	Occlusion	Clean
No adaptation	37.25 / 19.04	36.48 / 18.59	42.37 / 21.46	39.92 / 19.87	56.81 / 27.03
Pooled BN	40.65 / 18.08	42.90 / 18.94	53.87 / 23.47	35.17 / 14.83	59.17 / 27.25
Agent-wise, symmetric	53.11 / 23.55	50.69 / 22.24	56.60 / 25.20	37.06 / 17.48	58.76 / 26.69
Agent-wise, ego-anchored (AgentNorm)	51.98 / 24.35	49.83 / 22.88	55.59 / 25.70	35.63 / 17.95	57.85 / 27.18
AgentNorm, EMA statistics ( $m{=}0.05$ )	51.12 / 24.17	–	–	–	–
Oracle: GT-supervised collab. BN †	57.13 / 26.75	–	–	–	–

TABLE V: Ablation on AttFuse (OPV2V). Only the collaborators are corrupted (severity 5) or nothing is corrupted (clean). Entries are [email protected] / [email protected] in %. † Uses ground-truth labels; reference only.

Corruption	No adapt.	Pooled BN	Agent-wise (sym.)
Fog	2.44 / 1.63	41.74 / 15.39	41.71 / 15.54
Motion blur	0.66 / 0.33	32.50 / 10.31	33.34 / 10.11
Brightness	11.45 / 5.26	47.98 / 20.12	46.97 / 19.16
Occlusion	2.31 / 0.83	6.25 / 3.00	6.07 / 3.11

TABLE VI: Ego and collaborators corrupted with the same corruption (AttFuse, OPV2V, severity 5). [email protected] / [email protected] in %.

Method	Mean	Median	P95	Memory
No adaptation	254.32	184.38	495.70	2669
No adaptation (repeat)	255.19	185.33	496.40	2669
Pooled BN	255.28	184.73	497.33	2669
AgentNorm (ours)	256.65	186.16	501.99	2669

TABLE VII: Per-frame latency (ms) and peak GPU memory (MB) of AttFuse on OPV2V, collaborator fog at severity 5, including post-processing. 200 frames, the first 20 discarded, one RTX 3090.

Cooperative Perception

Cooperative perception lets connected vehicles, robots, and aerial agents combine sensor observations to understand scenes beyond a single viewpoint.

See all 112 papers

CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions
Mar 2, 2026Gong Chen, Chaokun Zhang, Pengcheng LvDiffusion-Based Denoising Cooperative Perception
School of Computer Science and Technology, Tianjin University · School of Cybersecurity, Tianjin University · School of Future Technology, Tianjin University
Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions
Apr 2, 2026Pengcheng Lyu, Chaokun Zhang, Gong Chen +2Cooperative Perception Autonomous Driving Perception
School of Future Technology, Tianjin University, Tianjin, China · School of Cybersecurity, Tianjin University, Tianjin, China · School of Computer Science and Technology, Tianjin University, Tianjin, China
BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception
May 1, 2026Kang Yang, Tianci Bu, Peng Wang +2Cooperative Perception Adaptive Learning
Renmin University of China · National University of Defense Technology

Mar 2, 2026J/K move · Enter open · S save

CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions

Gong Chen, Chaokun Zhang, Pengcheng Lv

School of Computer Science and Technology, Tianjin University · School of Cybersecurity, Tianjin University · School of Future Technology, Tianjin University

Diffusion-Based Denoising Cooperative Perception Autonomous Driving Perception Diffusion Models

Open paper AskPDF arXiv

Cooperative perception lets agents share information to expand coverage and improve scene understanding. However, in real-world scenarios, diverse and unpredictable corruptions undermine its robustness and generalization. To address these challenges, we introduce CoopDiff, a diffusion-based cooperative perception framework that mitigates corruptions via a denoising mechanism. CoopDiff adopts a teacher-student paradigm: the Quality-Aware Teacher performs voxel-level early fusion with Quality of Interest weighting and semantic guidance, then produces clean supervision features via a diffusion denoiser. The Dual-Branch Diffusion Student first separates ego and cooperative streams in encoding to reconstruct the teacher's clean targets. And then, an Ego-Guided Cross-Attention mechanism facilitates balanced decoding under degradation by adaptively integrating ego and cooperative features. We evaluate CoopDiff on two constructed multi-degradation benchmarks, OPV2Vn and DAIR-V2Xn, each incorporating six corruption types, including environmental and sensor-level distortions. Benefiting from the inherent denoising properties of diffusion, CoopDiff consistently outperforms prior methods across all degradation types and lowers the relative corruption error. Furthermore, it offers a tunable balance between precision and inference efficiency.

Abstract

Cooperative Perception

Explore similar work

CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions

Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions

BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception