- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper formulates burst deblurring as a 2D/SO(3) inverse problem: each blurry frame is modeled as the exposure-time integral of a shared hash-grid INR warped along rotational homographies. Motion is initialized from gyro data and refined with a Catmull–Rom spline on SO(3), and image and motion are optimized alternately without pretraining.
Critical strengths
- A physically grounded, depth-independent rotational model captures spatially varying blur while staying in 2D, avoiding NeRF-style rendering costs.
- Using gyro data as initialization, with a shared low-dimensional spline correction, is principled and stable.
- Pixel-query sampling makes test-time optimization practical at 12MP.
- The large real-world dataset and the stratified motion/luminance analysis are convincing, especially the gains under severe motion.
Critical weaknesses
- The main text does not describe how ground truth was obtained for handheld captures, which is critical to all reported results.
- No ablations isolate the contributions of gyro initialization, the spline parameterization, or the loss weighting. Since the individual components are established, the value of their integration needs empirical support.
- Some baselines (PI-CNN, Deblur-INR) operate far outside their intended regimes, and input conditions across methods are unclear.
Questions for authors
- How was ground truth captured and registered?
- How does performance change with fixed gyro motion or without gyro initialization?
- How robust is the method to gyro–camera synchronization and calibration errors?
- Do the authors plan to publicly release the dataset, including gyro data and ground truth?
4 comments
[2/2] Response to Reviewer RYJp
Q2. How does performance change with fixed gyro motion or without gyro initialization?
We would like to clarify that Supplementary Material Section D, Table 5 reports ablation studies regarding gyroscope initialization and motion refinement. We additionally conducted two new ablation studies to isolate the contribution of the neural image representation and the brightness weighting.
Specifically, we consider four ablation variants:
- No gyro: We remove gyroscope initialization and instead randomly initialize the motion trajectory, which is subsequently optimized using the spline.
- No spline: We use the gyroscope-derived motion trajectory without spline refinement , while keeping the image representation, forward model, and optimization schedule unchanged.
- No neural field: We replace the neural field with an RGB pixel grid using differentiable bilinear interpolation, while retaining the same motion model and reconstruction framework.
- No brightness weighting: We remove the brightness weighting in equation (5) by setting to 1.
The following table summarizes the numerical results:
Method Overall PSNR ↑ SSIM ↑ LPIPS ↓ Time (min) ↓ Mem. (GiB) ↓ Severe PSNR ↑ SSIM ↑ LPIPS ↓ Low-light PSNR ↑ SSIM ↑ LPIPS ↓ NBField (ours) 39.41 0.95 0.29 2.4 5.5 32.26 0.92 0.30 42.45 0.97 0.31 No neural field 32.09 0.78 0.51 2.5 5.8 27.97 0.78 0.54 33.17 0.76 0.50 No gyro 28.83 0.89 0.39 3.7 5.4 19.75 0.77 0.50 32.93 0.93 0.37 No spline 37.85 0.94 0.31 2.5 5.2 29.67 0.89 0.34 41.26 0.96 0.33 No brightness weighting 37.41 0.94 0.33 2.3 5.5 30.89 0.91 0.33 40.05 0.95 0.35
As shown in the table above, NBField achieves over 10 dB improvement in PSNR compared to the no-gyro variant, demonstrating the importance of accurate motion initialization. Compared to the no-spline variant, NBField achieves a 1.56 dB improvements overall and 2.59 dB improvement for severe motion, demonstrating that motion refinement with spline provides additional reconstruction benefits.
Furthermore, NBField outperforms the no-neural-field variant by more than 7 dB overall and 9.28 dB under low-light conditions. This demonstrates that the neural image representation plays a substantial role in reconstruction quality, beyond the benefits of the physical forward model and motion refinement. NBField also achieves over 2 dB improvement compared to the no-brightness-weighting ablation. All ablation variants have similar time and memory costs as NBField. We have incorporated these ablation results and a corresponding discussion into Section 4.3 of the revised manuscript.
Dear Reviewer RYJp, thank you again for your time and feedback. Could you let us know whether our response sufficiently addressed your concerns? If there are any remaining points that we could clarify, we are happy to discuss further.
Thank you for the authors' response. I believe that their response address most of my concerns.
Therefore, I raise my score from WR to WA.
[1/2] Response to Reviewer RYJp
W3. Some baselines (PI-CNN, Deblur-INR) operate far outside their intended regimes, and input conditions across methods are unclear.
Q1. How was ground truth captured and registered?
Q3. How robust is the method to gyro–camera synchronization and calibration errors?
Q4. Do the authors plan to publicly release the dataset, including gyro data and ground truth?