- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Block3D, a block-wise diffusion framework for efficient text-to-3D generation. Starting from the Cube discrete shape-token representation, Block3D partitions the 1024-token sequence into contiguous blocks, generates blocks autoregressively, and jointly denoises tokens within each active block. It further introduces confidence-guided intra-block correction to correct uncertain codes before a block is committed. On 100 held-out objects from TRELLIS-500K, Block3D improves geometric metrics over Cube while reducing mean generation time from 25.71s to 4.99s.
Critical strengths
-
The block-wise formulation substantially reduces the sequential decoding horizon, and the reported 5.15× speedup over Cube is impressive.
-
Block3D and Cube share the same tokenizer, decoder, training subset, and optimization budget, making the comparison relatively well controlled.
-
The training, decoding, attention-mask, and caching procedures are described in considerable detail.
Critical weaknesses
-
Limited methodological novelty: The central idea of autoregressive generation across blocks with bidirectional denoising inside each block is highly related to Block Diffusion. Moreover, the M2T/T2T editing mechanism is explicitly adapted from LLaDA2.1. The main novelty therefore appears to be their integration into Cube rather than a fundamentally new 3D generation algorithm. A stronger comparison against a directly adapted Block Diffusion baseline is needed to establish that the proposed 3D-specific components are genuinely necessary.
-
The main efficiency comparison is somewhat narrow: The headline 5.15× improvement is relative to Cube, whose token-wise autoregressive decoding is inherently sequential. Although other 3D generators are reported, the paper does not provide a controlled block-diffusion baseline using the same Cube representation and backbone. Thus, it is difficult to disentangle the gain from the general block-wise decoding paradigm from the proposed confidence-guided correction and training modifications.
-
Text-shape alignment does not improve: Block3D improves CD-L1, normal consistency, and F-score, but its CLIPScore is 23.24, lower than Cube's 23.87. Therefore, the claim of improving generation quality should be qualified: the improvement is mainly in geometric reconstruction metrics rather than consistently across all quality dimensions.
-
Limited evaluation scale and diversity: The main evaluation uses only 100 held-out objects, all sampled from TRELLIS-500K, with one deterministic generation per prompt. This makes the conclusions about general text-to-3D generation and robustness relatively weak. More diverse datasets, multiple random seeds/samples, and statistical significance would make the quality claims substantially stronger.
Questions for authors
-
Can the authors provide results across multiple random seeds and multiple generated samples per prompt?
-
Why does Block3D improve geometric metrics while reducing CLIPScore relative to Cube?
Thank you for the response. I'll keep the score unchanged.