Generating coherent videos grounded in a unified underlying world remains a major challenge, particularly under large viewpoint changes, where existing methods often struggle to maintain stable representations of individual objects. To this end, we introduce Totem, an object-centric 3D memory framework for world-consistent video generation. Totem first represents each selected object as a persistent 3D memory aligned to a shared world frame, assigning it a dedicated state. Based on these memories, we design a dual-stream 3D conditioning architecture that combines object memories with scene geometry for target-view synthesis. Moreover, these object memories constrain the model's attention with 3D structural information, thereby preserving object surfaces and relative spatial layouts. Extensive experiments on world-generation and object-centric benchmarks demonstrate that Totem generates videos depicting a more object-consistent 3D world under challenging camera trajectories, while supporting versatile applications.
Figures & tables
Figure 2: Overview of Totem, arranged from left to right. Standard video-network details and routine injection paths for text, camera, image, and mask information are omitted for clarity. From the reference image and target camera trajectory on the left, Totem constructs canonical object memories, aligns them to a shared world frame, and renders view-aligned dual-stream conditions. In the center, the conditions are separately encoded and projected, fused into control tokens, and injected into the frozen DiT through a ControlNet branch. On the right, two object-centric attention (OCA) mechanisms impose complementary constraints in canonical and world spaces to maintain object-level consistency.
Method
WorldScore Static
Camera Control
Object Control
Content Alignment
3D Consistency
Photometric Consistency
Style Consistency
Subjective Quality
Voyager [ 16 ]
77.62
85.95
66.92
68.92
81.56
85.99
84.89
71.09
Spatia [ 54 ]
72.63
75.66
52.32
69.95
86.40
89.10
80.09
54.86
Mirage [ 40 ]
73.60
55.36
74.17
42.09
92.21
93.95
96.91
60.50
EonWorld [ 8 ]
81.08
79.51
61.00
82.12
92.76
89.18
96.70
66.28
WorldScape-0.2 [ 25 ]
85.13
94.32
87.65
78.13
86.51
90.02
90.52
68.75
UniWorld-View [ 57 ]
85.53
97.72
88.98
86.61
91.63
94.11
76.55
63.12
Table 1: Quantitative comparison on WorldScore Benchmark. Bold indicates the best result; underlining indicates the second-best result.
Method
I2V Subject
I2V Background
Subject Consistency
Background Consistency
Motion Smoothness
Temporal Flickering
Video Similarity
Object Similarity
Chamfer Distance
MEt3R
ViewCrafter [ 49 ]
95.73
95.58
92.81
93.74
97.64
96.28
81.47
67.4
0.1423
0.1308
GEN3C [ 29 ]
96.38
97.42
93.86
95.33
98.57
97.52
83.92
70.3
0.1154
0.1057
Voyager [ 16 ]
96.72
97.18
93.28
95.06
98.17
96.85
83.24
69.5
0.1128
0.1103
Spatia [ 54 ]
97.34
97.63
94.15
95.27
99.16
98.44
84.56
71.1
0.1246
0.1176
WorldStereo [ 52 ]
96.93
98.06
93.98
95.82
98.48
97.36
83.76
71.4
0.1053
0.0964
Totem
97.76
97.86
95.04
95.62
98.82
97.75
85.08
73.2
0.0976
0.0818
Table 2: Quantitative comparison on ConsIDVid-Bench. Bold indicates the best result; underlining indicates the second-best result.
Figure 3: Qualitative results on video generation. Compared to the baselines, our model can generate videos with higher consistency while preserving the content in the input view.
Variant
PSNR ↑
SSIM ↑
LPIPS ↓
Object Similarity ↑
Chamfer Distance ↓
MEt3R ↓
Wan2.2 [ 36 , 35 ] with Camera Branch
17.31
0.528
0.466
48.5
0.289
0.361
+ Projected Point Cloud
21.04
0.653
0.347
53.7
0.234
0.284
+ Dual-Stream View Guidance
23.15
0.759
0.241
58.6
0.173
0.208
+ Dual-Stream View Guidance + OCA
25.67
0.838
0.139
65.3
0.124
0.138
Table 3: Ablation study of Dual-Stream View Guidance and Object-Centric Attention (OCA) on the OOD benchmark.
Figure 4: Applications: (a) Camera-controllable video generation. (b) 3D-aware video editing. (c) Long-range video generation.
Method
RotErr ↓
TransErr ↓
RPE-T ↓
RPE-R ↓
ATE ↓
AC3D [ 1 ]
16.87
0.358
4.12
1.58
0.842
CamI2V [ 56 ]
14.63
0.312
3.34
1.42
0.689
CameraNoise [ 53 ]
8.92
0.167
2.23
0.683
0.388
RealCam-I2V [ 22 ]
8.14
0.134
2.41
0.911
0.329
TriMotion-Pose [ 32 ]
5.38
0.146
1.57
0.462
0.253
Totem
3.82
0.077
1.06
0.418
0.148
Table 4: Quantitative comparison of camera-controllable video generation on the OOD benchmark. Translation-related errors are computed on scale-normalized trajectories, RPE is measured between consecutive frames, and ATE is calculated after global Sim(3) alignment.