- Rating
- 4(+1)
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents VIPER, a visual prior retrieval framework for multimodal point cloud completion. Instead of explicitly generating 3D priors, the method retrieves visual priors using pretrained visual representations and integrates them into point cloud features through a reliability gate. The authors evaluate VIPER on ShapeNet-ViPC, OmniObject3D-Completion, and KITTI, comparing its completion accuracy and inference efficiency with existing methods. The paper also introduces OmniObject3D-Completion, a new benchmark covering a broader range of object categories.
Critical strengths
-
The paper proposes a simple and effective approach to multimodal point cloud completion. Using retrieved visual priors instead of explicitly generated 3D priors is a well-motivated design choice that improves efficiency while maintaining strong completion performance.
-
The experiments cover multiple benchmarks, including ShapeNet-ViPC, OmniObject3D-Completion, and KITTI, providing a solid evaluation across different settings. The newly introduced OmniObject3D-Completion benchmark also covers a wider range of object categories and could be useful for future research.
-
The paper is well written and logically organized. The motivation is clear, and the method follows naturally from the limitations of explicit 3D prior generation. The main components are also explained clearly, making the approach easy to follow.
Critical weaknesses
-
The motivation for using qualitative examples and occlusion-impact maps in Figure 5 is not sufficiently clear. The authors should better explain how this evaluation supports their main claims.
-
The paper lacks a discussion of the potential limitations of visual prior retrieval, particularly the scenarios where it may be less effective.
Questions for authors
- What motivated the evaluation approach in Figure 5, particularly the use of occlusion-impact maps to compare visual prior retrieval with explicit 3D prior generation?
- The proposed reliability gate controls the contribution of retrieved visual priors during feature fusion. However, it is unclear whether the learned gating values actually reflect the reliability of visual evidence or simply act as feature-wise fusion weights. Could the authors clarify this distinction, given that no explicit reliability supervision is used?
3 comments
I thank the authors for their response, which has addressed my concerns. After reading the other two reviewers' comments and the authors' replies, I have decided to raise my score.
We Are Truly Grateful for Your Thoughtful Review
Dear Reviewer 2bxr,
Thank you sincerely for taking the time to read our response and for engaging so carefully with our work. Your questions helped us clarify what the visual evidence analysis shows, explain the role of the adaptive gate more precisely, and develop a fuller discussion of future directions.
We are grateful for the care and thought you have brought to this review. Your feedback has made the revised manuscript clearer and stronger, and we truly appreciate the opportunity to address your concerns.
Sincerely,
All Authors of Submission 816
Response to Reviewer 2bxr: Visual Evidence, Adaptive Gate, and Future Directions
We thank the reviewer for the constructive questions about the visual evidence analysis and the gate's interpretation.
Response to W1 and Q1 (why Figure 5 uses occlusion-impact maps). Figure 5 compares PGNet's explicit image-derived 3D prior and final completion with VIPER's completion and an input-sensitivity map. For the map, we hold the partial point cloud fixed, mask local image regions in turn, and measure how much the completion error increases. Regions with larger increases have more influence on the prediction under this perturbation. This makes the visual input's contribution to VIPER's recovered geometry inspectable even though VIPER does not generate an intermediate 3D prior. In the illustrated cases, errors in PGNet's intermediate prior coincide with completion artifacts, while VIPER recovers more faithful geometry and is sensitive to image regions associated with the missing structures. This sensitivity is consistent with VIPER's design: a frozen DINOv3 encoder supplies visual tokens, and point-conditioned top-K retrieval selects priors relevant to the partial geometry. These qualitative observations, together with the corresponding completion results, support the rationale for incorporating retrieved visual priors into point-cloud completion; stage-wise comparisons provide complementary quantitative evidence.
Revised manuscript: π Section 3.4, page 8, lines 400β412; π Appendix D.1, Table 10, page 21, lines 1122β1127; and π Figure 8, page 22, lines 1161β1187.
Response to W2 (scope and future directions). Our current evaluation focuses on object-level completion from paired RGB images and partial point clouds, with quantitative results on synthetic benchmarks and qualitative transfer to KITTI LiDAR. A natural next step is to study point-conditioned visual-prior retrieval in cluttered, dynamic, and large-scale outdoor scenes, where occlusion and variable cameraβLiDAR alignment make visual evidence more challenging to use. This direction is particularly relevant to multi-sensor perception for autonomous driving and mobile robotics: camera and LiDAR observations across viewpoints and time could jointly support reconstruction of surrounding geometry for perception and navigation. Beyond object-level completion, multi-view or temporal retrieval of visual foundation-model priors could support scene reconstruction and multi-modal 3D generation. We have reorganized Appendix F to discuss this broader scope and these future directions.
Revised manuscript: π Section 3.3, Figure 4, pages 7β8, lines 373β381; and π Appendix F, page 26, lines 1350β1360.
Response to Q2 (what the gate represents). The gate is a learned channel-wise fusion weight, conditioned on each point token and its retrieved visual message. It is trained through the completion objective without explicit reliability supervision, so its values should be understood as adaptive fusion weights rather than calibrated reliability scores. Its role is to adjust the strength of visual-prior injection for different point tokens and feature channels. We compare full VIPER with the variant without the learned injection gate in two settings:
The dash denotes removal of the learned injection gate; in OmniObject3D-Completion variant D, the projected visual prior is added directly to the point tokens. Cabinet uses CD in units of 10^-3 and [email protected]; OmniObject3D-Completion uses CD in units of 10^-4 and [email protected]. The OmniObject3D-Completion results are sample averages under the view-based split. Full VIPER performs better in both the single-category test and the broader joint-category benchmark, which extends evaluation from ShapeNet-ViPC's limited category coverage to 85 categories. These results support the effectiveness of adaptive gate design for visual-prior integration across both settings.
Revised manuscript: π Section 2.2, page 4, lines 168β183; π Section 3.5, page 9, lines 448β466; and π Appendix E.1, page 23, lines 1211β1236.