- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes Atomizer-IO, a sensing architecture that represents observations as individual measurements with acquisition metadata. Local cross-attention aggregates these observations into spatially anchored latent representations, which interact through a Transformer and are decoded at requested output locations. This design supports variable input channels, irregular geometries, and adjustable output density. The paper evaluates the architecture through separately trained models on eight Earth-observation benchmarks and two LiDAR datasets, covering classification, regression, and segmentation.
Critical strengths
-
The paper is well motivated and proposes a reasonable solution that aligns with the identified challenges.
-
The paper is clearly written and easy to follow.
Critical weaknesses
-
The methodological advancements of this approach over existing frameworks have not yet been fully substantiated. The architecture combines atomic representations, latent cross-attention, query-based decoding, and local geometric aggregation. While this combination is meaningful, the paper does not explicitly clarify what substantive capabilities or insights it adds beyond Atomizer, Perceiver IO, and existing geometry-aware aggregation methods. It appears to be a blend of many concepts, but there are no detailed experiments to support that this combination demonstrates meaningful synergy between the components. This limits the strength of its core contribution.
-
The discussion regarding the relationship with graph-based methods is insufficient. Designs such as local neighborhoods and anchor aggregation share similarities with information aggregation on graphs; the paper needs to clarify the connections and substantive differences.
-
The point cloud baselines are insufficient. While KPConv was mentioned as an earlier method, the paper should include newer, strong baselines such as PointNeXt and Point Transformer V3 for comparison under fair conditions.
Questions for authors
- What is the substantive advance over Atomizer and Perceiver IO beyond incorporating local geometric aggregation?
- What evidence shows that the unified interface offers practical advantages over task-specific architectures when accounting for both accuracy and computational cost?
3 comments
DALES provides a complementary comparison: both models receive one token per LiDAR return, removing the raster tokenization difference. Atomizer-IO reaches 66.7 mIoU versus 48.7 for Perceiver-IO. This supports the effectiveness of its spatial architecture on unordered inputs, although aggregation, latent allocation, and decoding also differ.
Second, regarding the contribution of the individual components, Appendix B already provides controlled ablations of the main sources of structure introduced by Atomizer-IO. These are independent ablations rather than a sequential addition of components:
- Local spatial encoding: reduces the input–latent interaction count from to without subsampling.
- Spatial RoPE (Appendix B.2): removing it reduces Cashew from 72.01 to 62.65 mIoU and MNIST from 99.37 to 29.48% accuracy.
- Target-local observation conditioning (Appendix B.3): removing it reduces Sen1Floods11 from 93.17 to 89.26 mIoU, with smaller effects on tasks relying less strongly on target-local measurements.
- Temporal aggregation (Appendix B.1): improves PASTIS by +0.47, +4.85, and +8.58 mIoU at 3, 6, and 12 timesteps, respectively.
These results show that local aggregation, relative spatial structure, target-local information, and temporal organization address different aspects of the problem rather than acting as redundant additions. We will make this analysis more visible in a future revision.
| Configuration | MNIST | Cashew | PASTIS (T=6) | BurnScars | Sen1Floods11 |
|---|---|---|---|---|---|
| Atomizer-IO w/o Spatial RoPE | 29.48 | 62.65 | 40.65 | 86.16 | 92.42 |
| Atomizer-IO w/o Local Obs. | – | 70.58 | 43.30 | 88.20 | 89.26 |
| Atomizer-IO w/o Temporal Agg. | – | – | 39.25 | – | – |
| Atomizer-IO | 99.37 | 72.01 | 44.10 | 88.81 | 93.17 |
W2 — Relationship and substantive differences with graph-based methods
Designs such as local neighborhoods and anchor aggregation share similarities with information aggregation on graphs; the paper needs to clarify the connections and substantive differences.
We will expand this discussion in a future revision. Mathematically, the Spatial Sampler can be viewed as constructing a bipartite geometric graph: in the encoder, atoms connect to their nearest spatial anchors; in the decoder, output queries connect to their nearest spatial anchors.
There are three main differences from standard GNNs and 3D superpoint graphs:
-
No atom-to-atom edge construction. Standard graph formulations commonly construct local edges between input nodes. For the approximately atoms of a Sen1Floods11 input, this would create a very large input graph. Moreover, multiple spectral measurements share exactly the same spatial coordinate. Atomizer-IO instead maps atoms directly to a much smaller set of spatial anchors.
-
The raster partition can be precomputed. For fixed geometries, the Voronoi assignment depends only on coordinates and can therefore be cached. In contrast, superpoint methods such as SPG/SPT use data-dependent geometric grouping.
-
Global communication occurs in the latent processor. Rather than propagating information through repeated local graph hops, Atomizer-IO applies global self-attention over the spatial latents, with their geometry represented through 2D RoPE.
W3 — Point-cloud baselines and 3D performance analysis
The point cloud baselines are insufficient. While KPConv was mentioned as an earlier method, the paper should include newer, strong baselines such as PointNeXt and Point Transformer V3 for comparison under fair conditions.
We agree that the comparison should include more recent point-cloud architectures. Table 4 already includes Superpoint Transformer (ICCV 2023), and in response to the reviewers we additionally evaluated Point Transformer V3 on FRACTAL.
We provide PTv3 with both modalities by associating VHR RGB values with the LiDAR points as fixed per-point features. PTv3 reaches 80.12% mIoU on the test set, compared with 78.4% for Atomizer-IO.
This result is consistent with the intended role of the 3D experiments. We do not claim state-of-the-art point-cloud segmentation. FRACTAL tests whether the same architecture can jointly process image and unordered LiDAR measurements without requiring them to first share a per-point feature representation. DALES goes one step further and tests the same Atomizer-IO spatial interface on a pure point cloud, without introducing a 3D-specific backbone.
The small FRACTAL gap to PTv3 shows that a specialized modern point-cloud architecture can perform slightly better when given an explicit RGB-to-point correspondence, while Atomizer-IO remains close using its more general independent-measurement interface. We will broaden this comparison further in a future revision.
Q2 — Practical advantages over task-specific architectures
What evidence shows that the unified interface offers practical advantages over task-specific architectures when accounting for both accuracy and computational cost?
Our goal is not to claim that a unified architecture should always outperform specialized models. Rather, we ask whether supporting heterogeneous inputs, irregular geometries, and flexible outputs comes at a substantial cost in accuracy or computation.
To isolate the effect of the architecture itself, all models in our main comparisons are trained from scratch under matched training conditions. We deliberately avoid pretrained weights because pretraining would make it difficult to separate gains coming from the architecture from gains coming from the amount or nature of pretraining data.
Under this controlled setting:
-
Competitive accuracy under matched training conditions (Table 2). Atomizer-IO ranks first on four and second on two of the six dense/spatiotemporal EO benchmarks, while using the same architecture across classification, regression, 2D segmentation, multitemporal prediction, and irregular inputs. This suggests that the unified interface does not impose a large accuracy penalty on standard raster tasks.
-
Graceful adaptation to changing sensor configurations (Table 3). A single trained checkpoint can be evaluated with different subsets of sensors or spectral bands simply by removing the corresponding atoms. No padding, missing-channel mask, or architectural modification is required.
-
Post-training control of inference cost (Section 4.3, Figure 5, Appendix C). Because predictions are produced through spatial queries, the number and location of output queries can be changed after training. The same checkpoint can therefore trade output density for decoder computation using dense, zone-probe, or quadtree querying without retraining.
The results also show where this flexibility has a cost. On DALES, specialized 3D architectures such as KPConv and SPT outperform Atomizer-IO, and on FRACTAL the newly evaluated PTv3 reaches 80.12% mIoU compared with 78.4% for Atomizer-IO. Atomizer-IO deliberately keeps the same general spatial interface used for 2D sensing rather than introducing a task-specific 3D backbone.
We view this as an important part of the evaluation: the purpose of the paper is to characterize when a unified sensing interface remains competitive, where it provides additional flexibility, and where stronger task-specific inductive biases are still beneficial.
Official Response to Reviewer DCBH
We thank Reviewer DCBH for the feedback. After considering the reviews, we have decided to withdraw the submission from ICLR 2027. We nevertheless provide this response to clarify the contribution and to document how the feedback will inform a future revision. We address the main concerns below and point to the relevant experiments and analyses already included in the paper and Appendix.
W1 & Q1 — Substantive advance over Atomizer / Perceiver-IO and component synergy
First, the advance over Atomizer (2025) and Perceiver-IO goes beyond adding local geometric aggregation. Atomizer introduced the atomic representation, but was designed only as an encoder for scene-level classification and was evaluated on a synthetic benchmark. Atomizer-IO changes how this representation is structured, scaled, and decoded:
In particular, Atomizer's global cross-attention requires every latent to attend to every input atom. On a single 5122×15 Sen1Floods11 input with L=2000 latents, this would require approximately 7.86×109 input–latent interactions. Atomizer-IO instead assigns each atom to a local spatial latent, reducing this to 3.93×106 interactions (99.95% reduction; Appendix B.7, Table 7). The number of spatial latents also scales with the number of observations, so additional input information can be allocated additional latent capacity without changing the model parameters.
Together with relative spatial encoding and a spatial query decoder, these changes extend the atomic representation from scene classification to regression, multitemporal prediction, and dense 2D and 3D segmentation. The query-based output interface also allows the same trained checkpoint to vary its output density after training, providing a direct accuracy–computation trade-off (Section 4.3).
Comparison with Perceiver-IO
Both architectures use an encoder–processor–decoder organization and support query-based outputs. The distinction is how information is organized and accessed:
For raster inputs, tokenization differs too: Perceiver-IO groups channels into pixel-level tokens, whereas Atomizer-IO represents each measurement independently. Although training protocols and metadata encodings are matched, this comparison evaluates the complete architectures rather than isolating spatial anchoring alone.
Both models can also condition predictions directly on observations at the queried location. We remove this pathway to test their dependence on local evidence when decoding from the latent representation:
Removing local observations reduces Perceiver-IO performance by 12.8 points on BurnScars and 16.4 on Sen1Floods11, compared with 0.6 and 3.9 for Atomizer-IO. Without this pathway, Atomizer-IO retains 88.2 and 89.3 mIoU, respectively, versus 70.6 and 75.8 for Perceiver-IO. These results suggest that Atomizer-IO better preserves information needed for prediction in its latent representation on these tasks. On PASTIS, removing local observations changes neither model substantially; the performance gap remains, but this experiment alone does not identify its cause.