- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies 3D inconsistency in camera-controlled video of a few hundred frames: objects drift, appear or disappear, pick up local artifacts, or the scene layout changes. The claim is that geometry-reward post-training such as VideoGPA and World-R1 gives each video one scalar, so a local failure is hidden by the rest of the clip (the paper's term is "washes out").
LoGo reconstructs the generated video with VGGT, voxelizes the fused point cloud (edge length 0.1 times the P90 scene depth), and scores each voxel by the mean RGB and depth reprojection error of the pixels that fall in it (Eq. 1). The group-normalized local score is mixed 1:1 with a video-level reprojection reward in DiffusionNFT's optimality-probability space (Eq. 2). Voxel scores are then averaged onto the latent patches they project to (Eq. 3). The training schedule also inserts HPSv3 and a camera-error reward. The paper adds TrajectoryBench: 2,000 image-plus-trajectory examples, with easy/medium/hard splits, indoor/outdoor/door-transition scenes, and up to 7–8 camera motions in 240 frames, including revisits.
Lingbot2, UniWorld and Lyra2 (all 14B) are post-trained on 1,700 DL3DV scenes and tested on TrajectoryBench and a camera-conditioned DL3DV hold-out. Reported metrics are reprojection PSNR from VGGT and from Depth Anything V3, Gaussian-splatting PSNR, MVCS, epipolar error, RPE, and VideoReward VQ. LoGo improves the consistency metrics over the base models, the authors' reimplementations of VideoGPA and World-R1, and a Global-only ablation. For Lingbot2 the paper reports +2.2 dB PSNR-D and a 26% lower epipolar error on TrajectoryBench, and +2.7 dB and 37% on DL3DV. The gap is larger on harder trajectories (Table 3) and longer videos (Fig. 8). Ablations vary the localization (voxel, frame, 2D patch, window), the reward recipe, the voxel size, and the RL algorithm (Flow-GRPO, DRaFT).
Critical strengths
S1. The comparison that isolates the method is the authors' own Global-only run. It uses the same reward model, the same RL algorithm and the same training recipe.
- LoGo is better on every consistency metric for all three base models (Tables 1–2).
- Voxel localization beats frame-level, 2D-patch and window localization (Table 4; PSNR-D 17.2 vs. 15.7 and epipolar error 1.381 vs. 1.726 against Global-only).
- The advantage grows with difficulty (Table 3, Lingbot2 PSNR-D: +1.0 dB on Easy vs. +2.5 dB on Hard) and with length (Fig. 8.).
The added cost is 9 seconds in a 1,920 second step (Efficiency paragraph in §3; 64 H100s). The same reward is applied to three 14B models: Lingbot2 is autoregressive with a KV cache, Lyra2 generates chunks with a 3D cache, and UniWorld is bidirectional.
S2. TrajectoryBench is a harder camera-control test than WorldScore. The tasks leave the first view, revisit a region, pass through a door, and put several camera motions in one 240-frame video. There are difficulty splits, stylized scenes, and paired standard errors in the appendix. DL3DV is also evaluated with camera conditioning. The authors say they will release code, checkpoints and the benchmark. WorldScore uses 80 frames and one camera command, so it does not produce the long single-clip failures in Fig. 1. It is not the only revisit evaluation already available: the introduction cites MIND (Ye et al., 2026), which tests revisit consistency with closed-loop actions rather than an open-loop camera trajectory.
Critical weaknesses
The tables do not yet show that a viewer would see more consistent video, or that the gain over prior methods comes from the spatial reward.
The training reward is a VGGT(-Ω) RGB-D reprojection error. PSNR-V is the same kind of score. PSNR-D and MVCS are also reprojection metrics, and RPE uses VGGT poses. HPSv3 in Table 5 is one of the interleaved training rewards. Section 3.2 and Fig. 3a/c show that blurring and desaturating can lower this reward. VR-VQ is the reported quality number that is not a training reward, and there is no human study. Epipolar error does not use that reconstruction. It drops clearly for Lingbot2. On DL3DV the other two models move less: UniWorld and Lyra2 gain +0.6 dB and +0.8 dB PSNR-D, and epipolar error falls by 5% and 24% (Table 2).
Section 4.2 says VideoGPA and World-R1 were built on WAN, an 80-frame model without camera control, and that the authors extend them to this setting. It does not say whether that extension uses the same data, the same number of steps, or the HPSv3 and camera rewards used for LoGo and Global-only. On Lingbot2 (Table 1), Global-only is still a scalar reprojection reward, but it is already at PSNR-D 17.1 and RPE 11.2°, against 16.1 and 13.1° for VideoGPA. In Table 5, adding interleaving alone moves RPE from 11.2° to 8.9°. The gap to the prior methods can therefore come from DiffusionNFT and the training schedule. Table 9 points the same way: with Flow-GRPO and DRaFT (UniWorld) the margin over Global-only is about 0.1–0.2 dB, and on the Flow-GRPO hard split the epipolar error goes from 1.500 to 1.553. The caption still says the advantage persists for every post-training algorithm.
Questions for authors
-
Baseline setup. Section 4.2 says VideoGPA and World-R1 are extended to the camera-controlled setting. Did that extension, and Global-only, use the same data, step budget, and HPSv3/camera interleaving as LoGo? If not, what happens if the VideoGPA or World-R1 reward is trained inside the same DiffusionNFT run and the same schedule?
-
Evidence outside the training reward. The training reward, PSNR-V, and RPE depend on VGGT; PSNR-D uses Depth Anything V3. Section 3.2 shows that blur and desaturation can lower the VGGT reward. Is there a viewer comparison on consistency and image quality, or a metric the reward does not optimize (frame sharpness or saturation, or RPE from a pose estimator other than VGGT)?
-
Shared voxel grid (Eq. 2). What are and ? The 16 rollouts are separate VGGT reconstructions. How do they share one voxel grid, in coordinate frame and scale, and how is a voxel scored when only some rollouts observe it?
6 comments
Response to Reviewer gjBs
Evidence outside the training reward. The training reward, PSNR-V, and RPE depend on VGGT; PSNR-D uses Depth Anything V3. Section 3.2 shows that blur and desaturation can lower the VGGT reward. Is there a viewer comparison on consistency and image quality, or a metric the reward does not optimize (frame sharpness or saturation, or RPE from a pose estimator other than VGGT)?
We totally agree that evaluating metrics should fall outside the training reward, and we do exactly this. We would first like to clarify a misunderstanding.
Clarification: Our goal is to improve 3D consistency while preserving other aspects of video generation, including video quality and camera control. Blur and desaturation do not “lower the VGGT reward” as you mention --- on the opposite, they increase the VGGT reward at the expense of video quality (Sec 3.2, L187-192), i.e. they are "reward hacking" behaviors. The design of LoGo, which includes local and global blending and reward interleaving, aims to combat this behavior. VR-VQ, a video quality metric, is exactly the metric to catch this, and it is not used in any training.
Metrics not used in training: LoGo’s evaluation contains various metrics that are not used in training.
For 3D consistency, which is LoGo’s main goal, we only train with VGGT reward and evaluate 3 other independent metrics that are not used in training. PSNR-D comes from Depth Anything V3, a model that is never used in training. PSNR-GS comes from Gaussian reconstruction, which is an alternative 3D reconstruction method that is different from depth estimation, and thus PSNR-GS is an unbiased metric completely unused in training. Finally, epipolar error is based on geometry: epipolar constraint rather than a reconstruction model, which is also outside of the training signal.
For video quality, we use VR-VQ, a video quality metric not used in training which can capture aspects such as blur, desaturation, or otherwise aesthetic degradation. LoGo maintains and largely improves VR-VQ (Table 1, Table 2), showing that it successfully combats reward hacking and preserves (even improves) video quality, in addition to improving 3D consistency.
For camera pose, we used RPE from VGGT in the main tables since it is the most accurate pose estimation model. We additionally show camera RPE from another pose estimator, Depth Anything V3, which highly agrees with the VGGT: on average, its rotation varies from VGGT less than 1.6% and translation less than 3.6%. We show the full VGGT and DA3 metrics below:
| Family | Model | Rot (VGGT) | Rot (DA3) | Trans (VGGT) | Trans (DA3) |
|---|---|---|---|---|---|
| LingBot | Base | 13.2 | 13.5 | 0.108 | 0.111 |
| LingBot | VideoGPA | 13.1 | 13.1 | 0.107 | 0.111 |
| LingBot | World-R1 | 13.1 | 13.2 | 0.108 | 0.110 |
| LingBot | Global | 11.2 | 11.2 | 0.102 | 0.105 |
| LingBot | LoGlo | 8.9 | 8.8 | 0.103 | 0.107 |
| UniWorld | Base | 13.8 | 14.1 | 0.132 | 0.136 |
| UniWorld | VideoGPA | 13.8 | 14.0 | 0.132 | 0.135 |
| UniWorld | World-R1 | 13.1 | 13.4 | 0.129 | 0.133 |
| UniWorld | Global | 13.3 | 13.5 | 0.126 | 0.130 |
| UniWorld | LoGlo | 14.0 | 14.1 | 0.130 | 0.133 |
| Lyra | Base | 7.9 | 8.3 | 0.100 | 0.106 |
| Lyra | VideoGPA | 7.7 | 7.7 | 0.099 | 0.104 |
| Lyra | World-R1 | 7.7 | 7.9 | 0.101 | 0.105 |
| Lyra | Global | 7.6 | 7.7 | 0.099 | 0.104 |
| Lyra | LoGlo | 7.5 | 7.7 | 0.101 | 0.106 |
Human evals: In addition to all the non-training metrics we evaluate, we additionally add human evaluation of LoGo vs. other baseline methods in 3D consistency on 150 video pairs based on stratified random sampling (to cover each difficulty level proportionally). We show the win rate of LoGo vs. each method (ties excluded) ranked by three independent annotators below. LoGo shows significant advantage, with 2.6x to 7.6x win rates.
| Win rate | |
|---|---|
| LoGo vs. Base | 3.4 : 1 |
| LoGo vs. VideoGPA | 2.6 : 1 |
| LoGo vs. World-R1 | 7.6 : 1 |
The tables do not yet show that a viewer would see more consistent video
Our metrics measure 3D consistency by measuring depth reprojection error (PSNR-V & -D), gaussian reconstruction error (PSNR-GS), MVCS, and epipolar error. In addition to the quantitative analysis, we also provide qualitative comparisons in Fig 6 and in video format in the supplementary zip folder. The purpose of the qualitative comparisons is to demonstrate the advantage of LoGo in generating more consistent videos – for example, maintaining the subway entrance scene rather than changing it into a different room (keyframes in Fig 6 first row, video in videos/baseline_comparison/0/) or removing hallucinated column-like artifacts (keyframes in Fig 6 second row, video in videos/baseline_comparison/3/).
Response to Reviewer gjBs
Shared voxel grid (Eq2). What are and ? The 16 rollouts are separate VGGT reconstructions. How do they share one voxel grid, in coordinate frame and scale, and how is a voxel scored when only some rollouts observe it?
is the mean of voxel 's voxel error across rollouts and is the normalization factor based on cross-rollout standard deviation - this is the standard normalization step to transform voxel errors into [0,1], the “optimality probability” used in DiffusionNFT, as defined in Sec 3.3 in the DiffusionNFT paper. Since the initial (conditioning) view is shared across rollouts, we use the camera frame of that view as the coordinate frame and voxel size of 0.1*P90 depth of the shared conditioning frame, so that various rollouts are comparable. If a voxel is observed by less than 16 rollouts but no less than 2, it is normalized within the subset of rollouts that observe it. If it is observed by less than 2 rollouts, it is skipped since standard deviation for normalization cannot be calculated (the corresponding cells later receive a neutral score of 0.5 during optimization). This affects less than 1% of the cells in practice.
Response to Reviewer gjBs
We thank reviewer gjBs for your review! Thank you for highlighting the importance of our global-only ablation and the value of TrajectoryBench. Our goal is to improve 3D consistency while preserving other aspects of video generation such as video quality and camera control. To achieve this, LoGo has three components that work together: credit assignment provides good consistency, but when used alone can induce reward hacking; local-global blending extends the Pareto frontier in the quality-consistency tradeoff; reward interleaving combats reward hacking. We address your question below:
The baseline methods and global-only are all trained on the same data and till convergence (thus step budget is not a limit). Reward interleaving, along with localized credit assignment and local-global blending, are three components of LoGo's method (Sec 3.1-3.3). For a fair comparison with existing methods, we stay faithful to the design choice of each method regarding post-training effectiveness and video quality. For example, VideoGPA is a two-stage method with rollout, DPO data pair selection via specific heuristics, and DPO training. Its recipe contains "preserving the base model’s visual quality" (Section 1, VideoGPA paper) by doing data filtering (Section 3.4, VideoGPA paper). We preserve these design choices for a fair recipe comparison.
Local-global blending and reward interleaving are important parts of the LoGo recipe (Table 5). These components need to work alongside with credit assignment to make LoGo effective. We do provide ablations to isolate out the effect of credit assignment in the LoGo vs. global-only comparison (Table 1). Global-only and LoGo are trained on exact same settings (same interleaving, same data etc.), both till convergence. The advantage of LoGo beyond Global-only shows that our advantage to baselines is not just in DiffusionNFT and reward interleaving. In fact, as shown in the Pareto plot (Fig. 3b), reward interleaving combats reward hacking rather than increases consistency. All components of LoGo (Sec 3.1,3.2,3.3) work together to make it an effective method.