- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes ICOcc, an instance-centric framework for unsupervised monocular 3D occupancy prediction. Instead of reconstructing a unified scene-level occupancy field, ICOcc decomposes occupancy into multiple latent slots to model object-level geometries separately. The framework further introduces a query-based Instance Decoupling Network and an Instance-Anchored Learning Strategy with multi-view pseudo supervision. Experiments on KITTI-360 and CarlaOcc show improved occupancy prediction.
Critical strengths
-
The instance-centric occupancy formulation is well motivated and provides a meaningful alternative to conventional scene-level reconstruction.
-
The experimental results are consistent with the paper’s motivation, particularly in improving object boundaries and reducing trailing artifacts.
Critical weaknesses
-
The experiments do not fully isolate the benefit of the instance-centric formulation from the additional pseudo segmentation, depth, surface, and free-space supervision. A controlled scene-centric baseline with the same supervision would make the contribution clearer.
-
The evidence that learnable queries truly capture stable instance-level 3D shape priors remains indirect. The paper also lacks analysis of query capacity, such as sensitivity to the number of queries or behavior in crowded scenes.
Questions for authors
-
How much of the performance gain comes from the instance-centric formulation itself, rather than the additional pseudo segmentation, depth, and geometric supervision? Could the authors provide a scene-centric baseline using the same supervision signals?
-
Could the authors provide more direct evidence that the queries learn instance-level 3D shape priors?
3 comments
I appreciate the authors for the response. The above explanation makes sense to me. Therefore, I tend to maintain my score.
Thank you for the follow-up and for considering our clarifications and additional experiments.
Q1: Ablation on instance-centric formulation itself
Thank you for highlighting the need to isolate the contribution of the instance-centric formulation.
Table 5 (before revision) already includes a related ablation, "Predicting Empty-Space Scores." This variant predicts an additional score for empty space instead of fixing it to zero. As is discussed in Supplement D.1, because empty space is the complement of scene occupancy, predicting this score retains an explicit scene-level prediction task: the network can determine whether a point is occupied by adjusting the empty-space score, without relying entirely on the predicted instance geometries. This provides an alternative to learning occupancy through instance-level shape priors. Under the same supervision, this scene-centric variant achieves lower average RayIoU than ICOcc (10.9% versus 12.1%), supporting the benefit of deriving scene occupancy from instance-level predictions.
To provide a more direct comparison with conventional scene-centric prediction, we additionally evaluate a baseline that predicts scene density σ and computes opacity as α=1−exp(−σδ). A separate slot-assignment head predicts π=softmax(s), yielding slot probabilities pq=απq. Thus, scene occupancy is predicted independently of its partition into regions. This baseline uses the same view groups, pseudo segmentation, pseudo depth, surface and free-space objectives as ICOcc.
We have added the new ablation to the revised manuscript.
Q2: Evidence about instance-level shape priors learning
Thank you for requesting more direct evidence that the queries learn instance-level 3D shape priors.
To examine this directly, we have added cross-scene visualizations of 3D occupancy predictions from fixed query IDs to the revised manuscript. Please refer to Fig.3 (d, e). Each row shows predictions from the same query across scenes, alongside the input images. In the visualizations, the same query predicts similarly structured vehicle geometries or road regions in different scenes, suggesting that queries capture geometric regularities shared across scenes.
The analysis already provided in Supplement Table 4 (before revision) also offers complementary quantitative evidence. We measure each query’s semantic composition across test frames and compare it with independently randomized query identities in each frame. This permutation preserves the predicted regions and their geometry but destroys cross-scene identity associations. The original queries achieve higher consistency (74.4% versus 38.0%) and a lower switching gap (19.9% versus 54.2%). These results show that query identities exhibit non-random cross-scene organization, complementing the geometric evidence in the added visualizations.