- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
MindView evaluates whether image generators can produce a requested viewpoint of an indoor scene from multiple partial observations and a language instruction. It contains 1,500 samples from 513 scenes across three datasets and covers seven tasks, ranging from camera translation and rotation to viewpoint inference based on objects and spatial relations. The authors evaluate 11 existing generators and release 20,000 training examples. Fine-tuning BAGEL raises its Overall score from 40.0 to 64.4. They also propose MindCue, a training-free view selector designed to address the performance decline observed when more input views are provided.
Critical strengths
-
The task design is valuable. The seven tasks cover both explicit camera motions and viewpoint inference requiring object grounding and spatial relations. Composition or multi-cue inference is the hardest task for each evaluated generator, revealing specific limitations beyond aggregate scores (Table 2).
-
Benchmark construction and review are careful. The authors use captured target images and filter candidates using camera poses, visibility, and scene annotations. Three reviewers check ambiguity and context adequacy, and the training and evaluation sets have disjoint scenes (§3.2, Appendices A and C.1).
-
The evaluation is broad, and the main adaptation result is clear. The paper reports separate measures of content, viewpoint, visual quality, and geometric consistency, with partial validation against human ratings (§3.3, Appendix B.4). BAGEL-SFT improves over BAGEL on all seven tasks and all 42 task–metric combinations (Table 2, Appendix Tables 9–12).
Critical weaknesses
-
A single target image may penalize valid responses to semantic instructions. ROG’s distance, centering, and visibility constraints may not uniquely determine a camera position in continuous space; MCVI’s uniqueness checks mainly cover recorded frames (Appendix A.2 and Limitations). Yet the VLM judge compares the generation with one target image without seeing the instruction, while the geometric metrics measure pose agreement with that target (§3.3, Appendices B.2–B.3). A different view that satisfies the instruction could therefore receive a lower score. The ambiguity checks mitigate this risk, but the paper does not quantify it.
-
The contribution relative to existing generative spatial benchmarks could be explained more concretely. GSI-Bench[1] also evaluates spatially constrained image generation or editing and studies transfer from generative training to spatial understanding. MindView differs meaningfully through multi-view observations, camera-viewpoint inference, and captured target views. However, §1–2 mainly describe differences in task setup without showing which failure modes or conclusions specifically require these distinctions. A task-level comparison would clarify the benchmark’s added value.
[1] Zhu, M., Jiang, S., Zheng, H., et al. Exploring Spatial Intelligence from a Generative Perspective. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
-
The cause of the performance decline with additional views remains unclear. Expanding the context from six to ten views increases target-content coverage from 88.4% to 92.0%, yet lowers Overall for all 11 existing generators; their Semantic and Spatial scores also decline (§4.3, Figure 5, Appendix Table 13). MindCue’s advantage over count-matched random selection suggests that view relevance matters, but does not distinguish irrelevant-view interference from difficulty integrating more images or effects of input order and format. The decline persists for BAGEL-SFT after task-specific fine-tuning, making this distinction especially relevant. The evidence establishes that more views do not necessarily help, but does not isolate why.
-
The spatial-understanding transfer results lack an absolute performance reference. Table 3 compares only BAGEL and BAGEL-SFT. This paired comparison establishes the effect of fine-tuning, but representative understanding or unified models evaluated under the same input and scoring protocols would help place BAGEL-SFT’s performance in context. Moreover, the gains on MMSI-Bench and MindCube-Tiny are only 1.2 and 1.8 percentage points, respectively. Without a control matched for training volume, the source of these gains remains uncertain (§4.4, Table 3).
Questions for authors
- For ROG and MCVI, could the authors use the original instructions to manually assess generated views that differ from the target image but remain valid, and quantify how often single-target evaluation penalizes them?
- Compared with GSI-Bench and related benchmarks, which failure modes does MindView’s multi-view setting reveal that single-image spatial editing tasks cannot? Could the authors provide task-level examples?
- When expanding from six to ten views, how much of the decline is attributable to low-relevance additions versus difficulty integrating more images? Could the authors compare relevance-based selection with changes in view order and simpler count-matched selection policies?
- Could the authors evaluate representative spatial-understanding or unified models using Table 3’s protocols, and add a training-volume-matched control for the transfer results?
4 comments
Response to Reviewer Lsi6 (Part 2/3)
W2 / Q2. Contributions Beyond GSI-Bench
The central added value of MindView is to test whether a model remains faithful to the same real scene jointly constrained by multiple input images when generating a different view.
The single-image input in GSI-Bench does not provide direct observations beyond the original field of view. Even when a target GT is available for evaluation, differences in the generated image may reflect plausible completion of unobserved regions. MindView, by contrast, can check scene content and relations that are clearly shown in other input views but are not preserved in the generated output. For Rotation, for example, if another input image already shows a cabinet and a window along a wall, but the generated image turns the cabinet into a table or changes their spatial relationship in the scene, this constitutes a consistency error that can be verified against the input evidence. This directly tests whether models can integrate cross-view observations and respect these scene constraints when generating a new view.
Transfer to spatial understanding provides additional support. We evaluated the official GSI-Bench finetuned BAGEL checkpoint under the same evaluation protocol. Both fine-tuning approaches use the BAGEL backbone and generation supervision only.
| Model | SAT-v2 Micro | SAT-v2 Both-order | MMSI-Bench | MindCube-Tiny |
|---|---|---|---|---|
| Vanilla BAGEL | 58.0 | 27.3 | 31.0 | 34.7 |
| GSI-Bench BAGEL | 59.3 | 28.0 | 29.9 | 34.8 |
| MindView-BAGEL-SFT | 62.7 | 41.3 | 32.2 | 36.5 |
MindView outperforms Vanilla BAGEL on all three understanding benchmarks, and its gains on all four metrics are larger than those of GSI-Bench. In particular, on MMSI-Bench, MindView improves accuracy from 31.0% to 32.2%, whereas GSI-Bench decreases it to 29.9%. The more consistent gains across benchmarks in this comparison provide additional evidence for the training value of MindView's scene-level spatial generation tasks.
W3 / Q3. Effects of View Relevance, Count, and Order
We added input-order shuffling, duplicate inputs, and count-matched view selection to examine the roles of order, image count, and additional-view selection in the C10 decline.
| Setting | # Images | BAGEL | BAGEL-SFT | ΔC6 | ΔC10 |
|---|---|---|---|---|---|
| Fixed C6 | 6.0 | 40.0 | 64.4 | 0.0 / 0.0 | +1.0 / +1.2 |
| Fixed C10 | 10.0 | 39.0 | 63.2 | −1.0 / −1.2 | 0.0 / 0.0 |
| C10 Shuffle | 10.0 | 39.1 | 62.9 | −0.9 / −1.5 | +0.1 / −0.3 |
| C6 + 4 Duplicates | 10.0 | 39.6 | 64.1 | −0.4 / −0.3 | +0.6 / +0.9 |
| Geometric Selection | 7.4 | 38.7 | 63.6 | −1.3 / −0.8 | −0.3 / +0.4 |
| RandDrop | 7.4 | 39.6 | 64.1 | −0.5 / −0.3 | +0.5 / +0.9 |
| MindCue | 7.4 | 41.1 | 65.1 | +1.1 / +0.8 | +2.1 / +1.9 |
Scores are task-macro averages of Overall, and # Images denotes the average number of input images. ΔC6 / ΔC10 denotes the score difference relative to C6 / C10. Each pair is reported in BAGEL / BAGEL-SFT order.
-
Input-order shuffling. C10 Shuffle randomly permutes the same set of C10 inputs, keeping the anchor in its original position for tasks that have one. After shuffling, both models remain close to their original C10 scores and below their C6 baselines. This indicates that changing the input order alone does not resolve the performance drop in the tested setting.
-
Duplicate inputs. C6 + 4 Duplicates preserves the positions of the C6 views within C10 and replaces the additional views with copies of four non-anchor core views. With the same total of ten input images, it outperforms C10 by 0.6 / 0.9 points, but still falls 0.4 / 0.3 points below C6. This indicates that the added content accounts for much of the C10 decline beyond image count alone, highlighting the importance of selecting useful supplementary evidence.
-
Count-matched view selection. Geometric Selection, RandDrop, and MindCue retain the same number of additional views for each sample from the same C10 candidate pool, preserving all C6 views and the original relative order of all retained views. The added Geometric Selection control does not use the query and prioritizes views that add coverage of previously uncovered regions, overlap less with the core views, and have higher reconstruction confidence. MindCue still outperforms both controls, supporting the conclusion that selecting evidence according to the target requirements provides additional gains after controlling for image count.
Taken together, these controls suggest that the benefit of C10’s increased coverage is outweighed by the difficulty of integrating more images and interference from less task-relevant content. MindCue uses the query-derived target-view hypothesis and supporting evidence to prioritize useful supplementary views, limiting irrelevant context while achieving gains over C6 and count-matched alternatives.
Response to Reviewer Lsi6 (Part 3/3)
W4 / Q4. Reference Models for Spatial Understanding and Training Controls
We added reference models and a training-volume-matched control to assess the level of understanding performance and the source of transfer gains, respectively.
- Reference models. We include the spatial reasoning model SpaceR [1], the general understanding model LLaVA-OneVision-1.5 [2], the unified understanding and generation model Emu3.5 [3], and GSI-BAGEL-SFT [4] as a reference model trained on generation tasks. All follow the input and scoring protocol of Table 3.
| Model | SAT-v2 Micro | SAT-v2 Both-order | MMSI-Bench | MindCube-Tiny |
|---|---|---|---|---|
| SpaceR (7B) | 57.7 | 44.7 | 28.9 | 31.7 |
| LLaVA-OneVision-1.5 (8B) | 60.3 | 40.7 | 29.0 | 36.5 |
| Emu3.5 (34B) | 61.7 | 36.7 | 30.7 | 45.7 |
| GSI-BAGEL-SFT (7B) | 59.3 | 28.0 | 29.9 | 34.8 |
| MindView-BAGEL-SFT (7B) | 62.7 | 41.3 | 32.2 | 36.5 |
MindView-BAGEL-SFT achieves the highest scores among the listed models on both SAT-v2 Micro and MMSI-Bench. Emu3.5 performs better on MindCube-Tiny. Its world-modeling training, which emphasizes cross-view scene consistency, may be better suited to the spatial layout inference required by this benchmark.
- Training-volume control. We fine-tune the same BAGEL using MACRO [5], a general multi-image generation dataset. The selected samples contain an average of 5.8 input images, close to MindView's 6. Both groups use 20,000 training samples and 10,000 steps, generation supervision only, and the same core training hyperparameters.
| Model | SAT-v2 Micro | SAT-v2 Both-order | MMSI-Bench | MindCube-Tiny |
|---|---|---|---|---|
| Vanilla BAGEL | 58.0 | 27.3 | 31.0 | 34.7 |
| MACRO-BAGEL-SFT | 60.0 | 31.3 | 29.2 | 34.5 |
| MindView-BAGEL-SFT | 62.7 | 41.3 | 32.2 | 36.5 |
With training samples and updates matched, MindView outperforms MACRO on all four metrics, with gains of 10.0 and 3.0 percentage points on SAT-v2 Both-order and MMSI-Bench, respectively. MACRO improves on SAT-v2 but falls below Vanilla BAGEL on MMSI-Bench and MindCube-Tiny, while MindView improves on all three benchmarks. These results support the transfer value of MindView’s spatial generation tasks beyond the benefit of additional training alone.
[1] SpaceR: Reinforcing MLLMs in Video Spatial Reasoning. arXiv 2025.
[2] LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training. arXiv 2025.
[3] Emu3.5: Native Multimodal Models are World Learners. arXiv 2025.
[4] Exploring Spatial Intelligence from a Generative Perspective. CVPR 2026.
[5] MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data. arXiv 2026.
Thanks to the authors for adding the experiments and for their response to my questions. I think these experiments and replies have addressed my previous concerns, and I will maintain my original decision of weak accept.
Response to Reviewer Lsi6 (Part 1/3)
W1 / Q1. Single-GT Evaluation: Rationale and Robustness
We agree that valid alternative views may receive lower scores under a single GT, as noted in our Limitations. We examine the rationale for fixed-GT LLM scoring through comparison with the Instruction-aware LLM Judge and human ratings, the robustness of model comparisons through reference GT replacement, and the remaining penalties on valid alternatives through an oracle-view test.
The Instruction-aware LLM Judge gives consistently high scores (GPT-Image-2: 99.7 on both metrics), possibly rewarding plausible layouts without fully understanding the input scene or verifying all spatial constraints, both of which can be challenging for LLMs. Our judge agrees more closely with human scores (Pearson r: 0.9394 / 0.9386 vs. 0.7254 / 0.7557) and rankings (Spearman ρ: 1.00 / 1.00 vs. 0.40 / 0.40). This supports a fixed GT as a practical scoring reference for model-level comparisons.
Task means change by at most 0.8 points, and rankings remain highly consistent (Spearman ρ: 0.993 / 1.00 for ROG / MCVI). Only Nano Banana Pro and SenseNova-U1.5 swap ranks 4 and 5 in ROG. The main model comparisons are stable to the choice of a valid reference GT.
Even the most pose-distant valid alternatives among the retained candidates achieve Overall scores of 88.5 / 87.3 on ROG / MCVI, showing that the fixed-GT protocol preserves substantial credit for valid alternative views, although some reference-related penalties remain.