- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper identifies the challenge of Neural Fields to model large-scale signals such as astronomical simulations and fluid flows, using pure MLP networks, as they tend towards global representation rather than focusing on local features. It is pointed out that scientific signal representation should be evaluated using signal derivatives, as they represent the dynamics of the signal, rather than just measuring only the reconstruction accuracy. The introduced Local Basis Neural Fields (LBNFs) follow a hybrid method using polynomials combined with lightweight MLPs, where the input signal coordinates are mapped to polynomial features. These features are given as the input to the lightweight MLP to output the signal value for a given coordinate. The proposed LBNF increases the controllability of the representation by selecting the approximation level of the polynomials. Further, training anchor points are either fixed as a grid or varied during training to learn complex signal components more accurately. The results show that LBNF competes with the SOTA algorithms in representing large signals, achieving comparatively high performance.
Critical strengths
-
Introducing polynomials combined with lightweight MLPs as a hybrid approach increases the controllability of the representation. When using a pure MLP based network, the approximation level is mainly determined through the number of parameters it possess, while it is controlled by changing the depth and the width of the MLP in general. From the proposed LBNF, the architectural changes in MLPs for approximation are replaced with polynomials.
-
The representation results for signal reconstruction are at an acceptable level. The quantitative results in Table 01 show a significant increase in the LBNF’s PSNR improvement. The qualitative improvement in Figure 1 shows that LBNF tries to correctly learn the signal structure with fewer incorrect predictions during inference.
-
The additional ablation studies further experimentally provide the model performance under different scenarios and parameter variations, as shown in Table 2 and the appendix.
Critical weaknesses
-
Although the overall contribution is explained in the paper, it is hard to identify the different contributions to distinguish the novelty in the methodology. Specifically explain whether the Adaptive Anchor placement is a novel contribution or it is an existing method. If it exists, need to explain the novel way that has been used in LBNF.
-
Although the authors point out that it is essential to compare the derivatives of scientific signals, according to Table 01, the best performance in some derivative errors can be seen in SIREN, but not for LBNF. Need a detailed explanation as a justification for the result.
Questions for authors
-
Distinguish the contributions clearly. Is it only the LBNF, or are there multiple contributions? Clarify the novelty of the adaptive anchor points used in the methodology.
-
Provide justifications for why SIREN has better derivative preservation compared to LBNF, as in Table 01.
2 comments
Thank you for the clarifications. I agree with the explanations about the derivative concern. However, I am not fully convinced that the level of novelty could increase my score. Hence, I'll keep my acceptance rate the same.
Response to Lbau
We thank the reviewer for their positive assessment and constructive feedback. Below, we clarify our contributions, including the role of adaptive anchor placement, and explain the SIREN derivative results.
CW1/Q1: Contributions and novelty of adaptive anchor placement.
LBNF makes multiple contributions, including a new anchor-placement mechanism. Its components (local polynomials, Gaussian weighting, a small neural decoder) are individually established. Our contribution lies in how they are combined and placed, what can be proven about the result, and the accuracy this achieves on large scientific signals.
Adaptive anchor relocation. While adaptive basis placement is a well explored idea in classical numerical methods, our contribution is the relocation mechanism itself. LBNFs start from random anchors and relocate them during training through residual-driven split-and-merge combined with gradient updates (Sec. 3.2). Not only is this parameter neutral, but it also removes the need for signal-dependent initialization. Many other methods either fix their bases (Instant-NGP, ∂∞-Grid) or rely on a special initialization (NeuRBF, efunc). See Figures 3 and 20 for more details.
Approximation guarantees. The approximation rates themselves are classical. However, to the best of our knowledge we are the first to show that a hybrid neural field can attain these rates (Sec. 3.3). Because the rates are explicit in the polynomial order p and anchor spacing h, this makes p and h interpretable accuracy controls, and we show that trained LBNFs meet the predicted rates empirically (Figure 7, Appendix C.2). We have additionally clarified in Sec. 3.3 how these results explicitly relate to classical theory.
CW2/Q2: SIREN derivative results in Table 1.
SIREN and LBNF have comparable derivative accuracy in Table 1, with SIREN modestly ahead on some maximum-error and second-derivative metrics. This is not surprising, since SIREN is a single global network with smooth sinusoidal activations, so its derivatives are smooth everywhere. However, this global parameterization comes at a substantial cost in value accuracy and training memory (0.32 GB for LBNF versus 3.00 GB for SIREN). The LBNF results in Table 1 are also truncated. Each query point blends only its K=32 nearest anchors rather than all anchors, which intentionally keeps memory low on the larger scientific signals (Appendix D.2). Unlike SIREN, LBNFs expose truncation as an explicit control over this tradeoff, since blending more neighbors (larger K) reduces derivative error at higher memory cost (Table 2, Appendix C.4). This control matters for large scientific signals. All representations need more parameters for larger signals, but in a global network, such as SIREN, every query passes through the full network, so per-query cost grows with capacity. LBNFs instead add capacity through more anchors while each query blends only K of them, leaving users free to choose how much derivative accuracy (inter-neighborhood smoothness) to buy with additional compute.