Assessing the Marginal Utility of Exocentric Head Views in UMI-Style Large-FoV Wrist-Camera Manipulation

Yuhui Duan; Shi Jin; Yuntian Wang; Jin Wang; Siao Liu; Wenchang Gao; Zhaxizhuoma; Yan Ding

cs.ROOct 8, 2026

Assessing the Marginal Utility of Exocentric Head Views in UMI-Style Large-FoV Wrist-Camera Manipulation

Authors: Yuhui Duan, Shi Jin, Yuntian Wang, Jin Wang, Siao Liu, Wenchang Gao, Zhaxizhuoma, Yan Ding

Organizations: Soochow University · Independent Researcher · Shanghai Jiao Tong University · Fudan University ·

Abstract

Multi-view perception is often treated as a safe design choice for robot manipulation: if one camera is useful, more cameras should be better. We revisit that assumption in tabletop bimanual manipulation by comparing policies trained with two large-field-of-view (FoV) wrist cameras against policies that additionally receive a head view, using controlled-variable experiments on a real bimanual platform. Across three tabletop tasks, adding a head view does not consistently improve task completion or execution quality: when the wrist cameras already observe the objects, grippers, and goal regions, wrist-only policies form a strong baseline. Restricting the wrist-camera FoV increases the potential value of a head view, but performance improves most reliably when the added view supplies concentrated, task-relevant information: region-of-interest (ROI) cropping yields more consistent head-view gains than the uncropped image, which is dominated by background and task-irrelevant regions. The data-scaling results further suggest an interaction between FoV and demonstration count: wide observations improve coverage but may require more data to stabilize, and they may reach a higher performance ceiling once enough demonstrations are available. These results suggest that camera design should be framed as a task-relevance and information-density problem rather than as a simple count of input views.

Figures & tables

Figure 1: Overview of the study, organized by its three contributions and its key findings. Top: the guiding question and the experimental setting—a real bimanual platform with two large-FoV wrist cameras and one fixed head camera, evaluated on three tabletop tasks. \scriptsize1⃝ The controlled observation design crosses wrist-camera FoV (Large, D435-like; shown by representative wrist frames) with head-view input (NoHead, RawHead, ROIHead), yielding the controlled configurations G1–G6 evaluated in Sec. 4 . \scriptsize2⃝ Each rollout is scored with a quality-adjusted metric that separates high-quality success from coarse completion, illustrated by two Task B final states. \scriptsize3⃝ RISE-style action-sensitivity diagnostics: in the Task B example the wrist views carry most of the step-level action share ( $0.59+0.26$ versus $0.14$ for the head view), which contributes low-weight global context. Bottom band: key findings from the two complementary experiments—the Task A data-scaling trend, which suggests that large-FoV input needs more demonstrations but may reach a higher performance ceiling, and the Task B wrist-FoV scan, where the ROIHead-versus-NoHead FinalScore contrast is non-monotonic in wrist FoV ( $+21.0$ Large, $-5.3$ FoV120, $-7.9$ FoV90, $+29.2$ D435-like).

Figure 2: Task overview and initial layouts. Rows show Tasks A–C, and columns show Init01–Init03. Red annotations specify the task goals, with numbered assignments illustrated in Init01. In Task A, arrows map the four objects to storage positions 1–4. In Task B, the green target basket is circled, and the surrounding baskets to be nested are labeled 1–4. In Task C, arrows map plates 1–3 to rack slots, and boxes mark the rack region.

Symbol	Quantity	Definition
$n_{g}$	Successful grasps	Times a target object is securely lifted by the gripper.
$n_{p}$	Correct placements	Target objects placed or inserted into the assigned goal region.
$n_{s}$	Stable placements	Placements where the object retains its intended pose at the target after release.
$n_{r}$	Retries	Repeated grasp or alignment attempts after a failed attempt.
$T$	Executed steps	Executed low-level control steps in the rollout.
$n_{g,\mathrm{loc}}$ , $n_{p,\mathrm{loc}}$	Localized grasps and placements (Task B)	Grasps and placements executed on the correctly localized baskets.

Table 1: Directly observed scoring quantities. Only these quantities are manually recorded for each rollout; all derived scores in this section are computed from them by fixed formulas. Localization-related counts apply to Task B and Task C as indicated.

Figure 3: Camera configuration schematic using representative policy-input frames from the basket-nesting experiments. Top row: left-wrist, right-wrist, RawHead, and ROIHead inputs. Bottom row: representative left-wrist inputs under Large, FoV120, FoV90, and D435-like settings. The panels come from separate rollouts and therefore illustrate view geometry and task-content density rather than a frame-matched crop comparison.

ID	Wrist FoV	Head Type	Input Configuration	Purpose
G1	Large	NoHead	Large Wrist Only	Large-FoV dual wrist baseline.
G2	Large	RawHead	Large Wrist + RawHead	Analyze RawHead under the large-FoV wrist setting.
G3	Large	ROIHead	Large Wrist + ROIHead	Analyze ROIHead under the large-FoV wrist setting.
G4	D435-like	NoHead	Cropped Wrist Only	Simulate restricted wrist vision.
G5	D435-like	RawHead	Cropped Wrist + RawHead	Analyze RawHead under the small-FoV wrist setting.
G6	D435-like	ROIHead	Cropped Wrist + ROIHead	Analyze ROIHead under the small-FoV wrist setting.

Table 3: Six main experiment configurations.

Figure 4: G1–G6 bar plots for the three tasks. Each bar shows FinalScore split into the outcome contribution (solid) and the high-quality bonus (light top segment), following the Score Split column in Table 4 . Bars without a light segment complete rollouts without earning any high-quality bonus.

Figure 5: Summary matrix of mean FinalScore across tasks and configurations. The continuous heatmap uses a muted blue-green palette consistent with the style of Figure 4 ; lighter cells indicate lower FinalScore and darker cells indicate higher FinalScore.

FoV Setting	NoHead	ROIHead	Purpose
Large	F1 / G1	F2 / G3	Large-FoV baseline.
FoV120	F5	F6	Medium-FoV comparison.
FoV90	F7	F8	More restricted FoV comparison.
D435-like	F3 / G4	F4 / G6	Small-FoV comparison.

Table 5: Wrist-FoV experiment configurations.

Figure 6: Decomposition of the head-view contrast across wrist-FoV settings on Task B. (a) The FinalScore contrast

\Delta_{\mathrm{head}}

(ROIHead

-

NoHead) is positive under Large and D435-like but negative at the medium settings. (b) Metric-level changes explain this pattern: the localization rate improves under every FoV setting, whereas the Quality Success Rate flips sign at FoV120 and FoV90, where longer ROIHead trajectories violate the

T\leq 900

high-quality gate (the completion-rate change at FoV120 is zero); see Table 6 for the full per-setting values, including steps. Values are descriptive means over the fixed rollout slots.

Configuration	Wrist FoV	Head Type	Demonstrations
2W-Large	Large	NoHead	50 / 200 / 800
2W-D435Crop	D435-like	NoHead	50 / 200 / 800
3V-D435Crop-ROIHead	D435-like	ROIHead	50 / 200 / 800

Table 7: Data-scaling experiment configurations.

Figure 7: Scaling curves. The x-axis is the number of demonstrations. The y-axis is FinalScore. The curves include 2W-Large, 2W-D435Crop, and 3V-D435Crop-ROIHead, with descriptive bootstrap intervals.

Figure 8: Initial observability in the toy-transfer diagnostic. (a,b) The head view distinguishes whether the toy starts in the left or right bin. (c,d) The initial left- and right-wrist observations do not expose the target because of the bin walls. The panels document the visual information available at the initial decision stage; they are not rollout-success evidence.

RQ	Evidence	What it answers
RQ1	G2 $-$ G1, G3 $-$ G1	How much gain RawHead or ROIHead adds when wrist FoV is large.
RQ2	G5 $-$ G4, G6 $-$ G4; FoV scan (Table 6 ); G1 vs. G6	Whether restricted wrist FoV increases head-view value, and when that potential fails to raise the quality-adjusted score.
RQ3	G3 $-$ G2, G6 $-$ G5	Effect of ROI cropping relative to the raw head view under large and small wrist FoV.
RQ4	Data-scaling experiment (50/200/800 demonstrations)	How demonstration count interacts with the visual-input configuration.

Table 8: Research questions and the evidence that serves them. The rows follow the RQ order in the introduction; contrasts are computed from the G1–G6 results in Table 4 .

Task	Comparison	$\Delta$ Completion Rate	$\Delta$ FinalScore	$\Delta$ Quality Success Rate	$\Delta$ Steps
Task A	G2 $-$ G1 RawHead	+40 pp	-16.0	-40 pp	+70.0
Task A	G3 $-$ G1 ROIHead	+30 pp	-6.0	-20 pp	+75.0
Task B	G2 $-$ G1 RawHead	-10 pp	-1.1	-10 pp	+67.5
Task B	G3 $-$ G1 ROIHead	+20 pp	+21.0	+30 pp	-47.5
Task C	G2 $-$ G1 RawHead	0 pp	0.0	0 pp	-5.0
Task C	G3 $-$ G1 ROIHead	+20 pp	+12.2	+20 pp	-60.0

Table 9: Head-view contrasts under the Large FoV setting. The comparisons are G2

-

G1 and G3

-

G1. Values show changes relative to the Large FoV NoHead baseline G1. FinalScore contrasts are computed from unrounded means before one-decimal display.

Figure 9: Head-view contrasts under the Large FoV setting. Horizontal bars show the mean

\Delta

FinalScore for G2

-

G1 or G3

-

G1 relative to the G1 NoHead baseline. The zero line separates lower and higher mean scores relative to G1.

Panel of Figure 10 — Figure 10: Representative real-robot final states illustrating the distinction between completion and high-quality completion. Completion-only examples can satisfy coarse task progress while still losing the high-quality bonus because of unstable final pose or poor alignment; long execution and repeated attempts are additional scoring-protocol failure modes summarized in Table A2 .

Figure 11: RISE-style action-sensitivity example for RawHead and ROIHead on Task A. Heatmaps visualize $S_{v}(c)$ from Eq. F3 ; action-share values report $q_{v}$ from Eq. F4 within each selected step. The maps indicate local action sensitivity, not attention weights or rollout success.

Figure 12: RISE-style action-sensitivity examples across the three tasks. Heatmaps show $S_{v}(c)$ , and view-level shares are $q_{v}$ within each selected step. Wrist views typically respond near grippers, objects, and contact regions, while the head view provides lower-weight global context. These examples are diagnostic illustrations of view roles and are not success-rate evidence.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Figure B1 : Representative RawHead and ROIHead policy inputs from the basket-nesting experiments. RawHead retains broad scene context with lower task-region concentration, whereas ROIHead concentrates the task-relevant region. The panels come from separate rollouts and illustrate view geometry rather than a frame-matched crop comparison.

Figure C1 : RISE-style action-sensitivity comparison between NoHead and ROIHead under the restricted-wrist-FoV setting. NoHead contains only the two wrist views, while ROIHead adds the head view. In these representative single-step examples, wrist views have the larger $q_{v}$ values, while the head view provides auxiliary spatial cues.

Figure D1 : RISE-style head-view action sensitivity and representative target-box choices in the toy-transfer diagnostic. (a,b) For the two initial toy locations, the dominant high-response region overlaps the occupied bin and shifts with the visible toy location. The overlays visualize $S_{v}(c)$ and are interpreted spatially; color intensity is not compared quantitatively across panels. (c,d) In the shown wrist-only cases, the policy selects the left bin for both toy locations, yielding a correct box choice when the toy is on the left and an incorrect choice when it is on the right. (e) In the shown case with an added head view, the policy selects the right bin when the toy is on the right. The behavior frames are recorded from the head-camera viewpoint for visualization. These unscored examples do not estimate success rates, prove causal reliance, or establish the cause of the wrist-only left-bin preference.

Vision-Based Robot Control

Vision-based robot control uses camera images to guide robots’ navigation and manipulation through closed-loop perception and action.

See all 221 papers

Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?
Mar 23, 2026Boyang Cai, Qiwei Liang, Jiawei Li +11Multi-View Learning Generalization in Robotic Manipulation
The Hong Kong University of Science and Technology (Guangzhou) · Shenzhen University · Beijing Jiaotong University +1
Fisheye-VLA: Decoupling Coverage and Acuity for Manipulation with a Single Fisheye Camera
Sep 22, 2026Ziang Ren, Zike Yan, Raymond Zhang +2Robotic Manipulation Vision-Based Robot Control
Hong Kong Embodied AI Lab · The Chinese University of Hong Kong, Hong Kong SAR, China · DeepCybo +1
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
Oct 2, 2026Kush Hari, Justin Kerr, Nidhya Shivakumar +7Active Vision for Robot Manipulation Active Vision
UC Berkeley · Amazon FAR · Stanford University

Mar 23, 2026J/K move · Enter open · S save

Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?

Boyang Cai, Qiwei Liang, Jiawei Li, Shihang Weng+10

The Hong Kong University of Science and Technology (Guangzhou) · Shenzhen University · Beijing Jiaotong University+1

Multi-View Learning Generalization in Robotic Manipulation Robotic Manipulation Multi-View Video Generation

Open paper AskPDF arXiv

Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling behavior, and underlying mechanisms of multi-view data for robot manipulation. Controlled experiments show that, under both fixed and randomized backgrounds, multi-view demonstrations consistently improve single-view policy success and generalization. Performance varies non-monotonically with view coverage, revealing effective regimes rather than a simple "more is better" trend. Notably, multi-view data breaks the scaling limitation of single-view datasets and continues to raise performance ceilings after saturation. Mechanistic analysis shows that multi-view learning promotes manipulation-relevant visual representations, better aligns the action head with the learned feature distribution, and reduces overfitting. Motivated by the importance of multi-view data and its scarcity in large-scale robotic datasets, as well as the difficulty of collecting additional viewpoints in real world settings, we propose RoboNVS, a geometry-aware self-supervised framework that synthesizes novel-view videos from monocular inputs. The generated data consistently improves downstream policies in both simulation and real-world environments.

Abstract

Vision-Based Robot Control

Explore similar work

Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?

Fisheye-VLA: Decoupling Coverage and Acuity for Manipulation with a Single Fisheye Camera

EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras