- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The proposed PixGR uses pixel-space flow matching for sparse-view 3D reconstruction. The scene encoder extracts and caches input features in a single pass, while a lightweight generative decoder combines a noisy target image and camera parameters to iteratively predict a shared 3D Gaussian representation, which is then rendered to produce a denoised image. The proposed method outperforms in reconstruction quality on RealEstate10K, DL3DV, and ACID. However, there are clear precedents for this type of integrated generative reconstruction, and the current experiments have not sufficiently prove the value of the incremental design proposed in this paper.
Critical strengths
-
The performance improvement is clear. The PSNR of the RE10K extrapolation reaches 26.03 dB, which is higher than the 23.98 dB achieved by the SOTA generative baseline in Table 2. The deterministic decoder of the same scale in Table 3 achieves 24.34 dB, which supports the effectiveness of generative decoding in this architecture.
-
It shows practical efficiency and outputs reusable explicit scenes. Scene encoding is computed only once. The DL3DV experiment constructs a shared 3DGS using three target keyframes and then renders all 42 evaluation viewpoints.
Critical weaknesses
-
The distinctions from existing methods need to be further clarified. DiffusionGS [1] has integrated Gaussian prediction and rendering into the denoising process and demonstrated results in real-world scenes. PixWorld [2] also employs pixel-space flow matching and differentiable rendering.
-
The ablation studies seems insufficient. Table 3 supports the effectiveness of generative decoding, but lacks pixel-space/latent-space comparisons, making it difficult to confirm the specific benefits of avoiding VAE. Furthermore, the number of parameters does not account for the computational cost of iterations.
[1] Cai, Yuanhao, et al. "Baking gaussian splatting into diffusion denoiser for fast and scalable single-stage image-to-3d generation and reconstruction." ICCV, 2025. [2] Gao, Sensen, et al. "PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space." arXiv preprint arXiv:2607.05373 (2026).
Questions for authors
-
Compared to DiffusionGS and PixWorld, what specific new techniques have been introduced? Please specify whether PixWorld is a prior or concurrent work relative to this paper.
-
Can the authors provide comparisons with more closely related generative methods, as well as evidence isolating the benefits of the pixel-space design and iterative computation? DiffusionGS was compared only in a single-view setting, and PixWorld has not yet been included in the experiments. Please also specify the training resources and inference budget.
5 comments
Response #2
Table (a). Reconstruction quality and inference-time breakdown on RE10K with two context and three target views.
| Method | Encoder | Decoder | Formulation | PSNR↑ | SSIM↑ | LPIPS↓ | FID↓ | Encoder Time (s) | Decoder Time (s) | Rendering Time (s) | Total Time (s) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| DiffusionGS | - | DiT (24-layer) | DDPM | 23.10 | 0.801 | 0.184 | 4.11 | - | 1.73 | 0.007 | 1.73 |
| Variant-A | ViT (12-layer) | DiT (12-layer) | DDPM | 23.34 | 0.804 | 0.178 | 4.01 | 0.009 | 0.97 | 0.008 | 0.99 |
| Variant-B | ViT (12-layer) | DiT (12-layer) | flow | 23.89 | 0.825 | 0.173 | 3.92 | 0.009 | 0.33 | 0.008 | 0.36 |
| PixGR | VGGT | DiT (12-layer) | flow | 26.03 | 0.872 | 0.141 | 2.75 | 0.089 | 0.38 | 0.007 | 0.47 |
Table (b). Inference time for three target views as the number of context views increases.
| Method | 2 context | 4 context | 6 context | 8 context | 10 context |
|---|---|---|---|---|---|
| DiffusionGS | 1.73 | 2.39 | 3.21 | 4.29 | 5.36 |
| Variant-A | 0.99 | 1.39 | 1.81 | 2.36 | 2.91 |
| Variant-B | 0.36 | 0.49 | 0.63 | 0.83 | 1.02 |
| PixGR | 0.47 | 0.65 | 0.86 | 1.07 | 1.32 |
We have also updated Tables 1 and 2, Figure 5, and Appendix C.3 in the revised paper to include DiffusionGS results.
W1 & Q1: PixGR vs. PixWorld
PixWorld is concurrent work submitted to ICLR 2027, according to OpenReview.
Similar to DiffusionGS, PixWorld adopts a decoder-only architecture and thus suffers from the same computational inefficiencies discussed above in our comparison with DiffusionGS.
Furthermore, PixWorld predicts RGB images at high noise levels and switches to 3D Gaussian rendering only at low noise levels, resembling the generation-then-reconstruction pipeline discussed in Figure 1, which may lead to cross-view inconsistencies during generation. In contrast, PixGR directly generates a unified 3D Gaussian representation at each sampling step, preserving multi-view consistency throughout the generation process. Table (c) compares PixGR and PixWorld on RE10K one-view generation and shows that PixGR outperforms PixWorld with significantly higher efficiency.
Table (c). RE10K generation quality and inference time under a single-context-view setting.
| Method | PSNR ↑ | SSIM ↑ | LPIPS ↓ | FID ↓ | Time (s) ↓ |
|---|---|---|---|---|---|
| PixWorld | 17.66 | 0.651 | 0.407 | 22.45 | 30.88 |
| PixGR | 19.53 | 0.655 | 0.284 | 15.00 | 0.37 |
W2 & Q2: Pixel-space vs. latent-space generation
We use SD-VAE to encode target images into latents and train a latent-space DiT to denoise them conditioned on VGGT-encoded context tokens and target camera poses. The frozen VAE decoder converts the denoised latents back into target images, and a Gaussian head takes both context and target images to construct a shared 3D Gaussian representation. This implementation uses the same context images and target poses as PixGR, enabling the pixel-space versus latent-space comparison in Table (d) under matched settings.
Table (d). Pixel-space versus latent-space generation.
| PSNR↑ | SSIM↑ | LPIPS↓ | FID↓ | |
|---|---|---|---|---|
| latent-space | 23.38 | 0.826 | 0.179 | 3.93 |
| pixel-space | 26.03 | 0.872 | 0.141 | 2.75 |
As shown in Table (d), the pixel-space model achieves significantly better performance than the latent-space variant, highlighting the advantages of direct pixel-space generation.
W2 & Q2: Iterative Computation
As shown in Table (e), PixGR (one-step) still outperforms the regressor (one-step), demonstrating that the benefits of pixel-space generative decoding do not rely on iterative computation.
To further evaluate the effect of iterative computation, we implement an iterative regressor starting with two context images and three blank target inputs, feeding rendered target views back into the decoder at each subsequent step. As shown in Table (e), increasing the number of iterations degrades the regressor's performance by amplifying blurry artifacts in underconstrained regions, whereas PixGR's performance consistently improves with more iterations.
Table (e). One-step and ten-step reconstruction results for the regressor and PixGR.
| Method | Iterations | PSNR↑ | SSIM↑ | LPIPS↓ | FID↓ |
|---|---|---|---|---|---|
| Regressor | 1 | 24.34 | 0.821 | 0.166 | 5.42 |
| PixGR | 1 | 25.78 | 0.867 | 0.145 | 3.12 |
| Regressor | 10 | 23.94 | 0.817 | 0.170 | 5.72 |
| PixGR | 10 | 26.03 | 0.872 | 0.141 | 2.75 |
Q2: Training resources and inference budget
We use 8 A100 GPUs for training and a single A100 GPU for inference. Inference requires 13 GB of GPU memory per scene (2 context views and 3 target views).
Dear Reviewer YbGc,
As the discussion phase draws to a close, we would like to sincerely thank you for your time and thoughtful feedback. We hope that our rebuttal and additional experimental results have adequately addressed your concerns and provided further clarity on our contributions.
If you find that your previous concerns have been sufficiently resolved, we would be grateful if you could kindly consider reflecting these clarifications in your final evaluation. Of course, we would also be happy to address any remaining questions.
Thank you again for your valuable time and consideration.
Best regards,
The Authors
Response #1
We thank the reviewer for the helpful feedback.
W1 & Q1 & Q2: PixGR vs. DiffusionGS
The main methodological differences between PixGR and DiffusionGS are the encoder–decoder architecture and the flow-matching formulation.
A. Methodological Differences
1. Decoder-only vs. Encoder–Decoder Architecture.
DiffusionGS adopts a decoder-only architecture that jointly processes context and target images throughout the entire transformer, leading to computational inefficiencies in three ways:
(1) Across target viewpoints: The same context images must be repeatedly processed when conditioned on different target viewpoints.
(2) Across diffusion sampling steps: Context images must be reprocessed at every sampling step.
(3) With increasing context views: The computational cost grows substantially as the number of context images increases.
In contrast, PixGR adopts an encoder–decoder architecture that encodes clean context images only once into latent representations, while iterative generation is performed entirely within the decoder. This design significantly reduces computational redundancy across diffusion sampling steps and target viewpoints, and improves efficiency when processing larger numbers of context views.
Moreover, since the context encoder is executed only once, PixGR can leverage large pretrained models, such as VGGT, as the context encoder to extract stronger geometric features without substantially increasing the computational cost of iterative generation.
2. DDPM vs. Flow Matching.
DiffusionGS adopts a DDPM formulation, generating target views through a stochastic reverse denoising process. In contrast, PixGR employs flow matching, which learns a continuous transport from noise to clean target images and performs sampling using an ODE solver. Our experiments demonstrate that flow matching achieves higher sampling efficiency than DDPM.
B. Controlled Ablation Studies
To systematically evaluate these design choices, we conduct ablation experiments on RE10K, with all methods trained and evaluated using 2 context views and 3 target views. Since DiffusionGS officially supports only a single context view, we fine-tune it with 2 context views following its official training protocol. The results are summarized in Tables (a) and (b) below.
All inference times are measured on a single A100 GPU. Encoder Time is the one-time context-image encoding cost; Decoder Time covers iterative generation, including intermediate Gaussian renders; and Rendering Time is the final novel-view render from the completed Gaussians.
1. Effect of the encoder–decoder architecture (DiffusionGS → Variant-A). We split the original 24-layer DiT into a 12-layer ViT context encoder and a 12-layer DiT decoder, retaining the DDPM formulation. Variant-A achieves comparable or slightly better reconstruction quality with a 1.75× speedup (1.73s → 0.99s), demonstrating the advantage of separating context encoding from iterative generation.
2. Effect of flow matching (Variant-A → Variant-B). We replace DDPM with flow matching while keeping the architecture unchanged. We use DiffusionGS's official 30 sampling steps for DDPM and 10 steps for flow matching. We find that 10-step sampling produces clean images with flow matching but leaves residual noise with DDPM (Figure 8 of the revised paper). Variant-B achieves better performance with an approximately 3× speedup (0.99s → 0.36s).
3. Effect of the pretrained context encoder (Variant-B → PixGR). Since context images are encoded only once, we can leverage large pretrained models with limited computational overhead. Replacing the 12-layer ViT with VGGT significantly improves reconstruction quality, while only increasing inference time from 0.36s to 0.47s.
4. Efficiency with increasing context views. We compare the inference efficiency of all four methods as the number of context views increases in Table (b) (better viewed in Figure 9 of the revised paper). While DiffusionGS incurs rapidly growing computational costs, Variant-A substantially reduces this overhead by avoiding repeated context encoding. Variant-B further improves efficiency through flow matching. PixGR maintains high efficiency even with the larger VGGT encoder, demonstrating the advantage of our encoder–decoder architecture.