SyncVid: World-Equivariant Diffusion for Synchronized Video Generation

Farhad G. Zanjani; Animesh Karnewar; Fatih Porikli; Amirhossein Habibian

cs.CVOct 22, 2026

SyncVid: World-Equivariant Diffusion for Synchronized Video Generation

Authors: Farhad G. Zanjani, Animesh Karnewar, Fatih Porikli, Amirhossein Habibian

Organizations: Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.

Abstract

Generating multiple videos of a dynamic scene from a single reference video requires synthesizing both observed and unobserved content consistently across viewpoints. Existing camera-control methods for video diffusion typically rely on architectural mechanisms, including camera embeddings, cross-view attention, and geometric conditioning. Although effective for static scene content, these approaches often struggle with the fine-grained, dynamic geometry that must remain coherent across views and over time. We synchronize the diffusion process itself by sampling the Gaussian noise prior in a canonical 3D space derived from the source video and rasterizing it into target cameras, rather than sampling independently in each 2D image plane. Our method, SyncVid, lifts a monocular video into a canonical 4D representation, associates noise with scene geometry and unseen space, and rasterizes the resulting structured noise into arbitrary views. Because rendering can introduce local correlations, we further propose a cross-view-consistent whitening procedure that decorrelates neighboring pixels while preserving correspondence across views. The structured noise serves as the diffusion prior for a LoRA-adapted pretrained video diffusion model, requiring no architectural modifications. By enforcing spatiotemporal and cross-view coherence at the source of stochasticity, SyncVid generates synchronized videos and improves both perceptual quality and cross-view consistency in our experiments. Project page: https://qualcomm-ai-research.github.io/SyncVid-Webpage.

Figures & tables

		View Synchronization				Temporal Consistency	Camera Accuracy
Method	Generation Length	Mat. Pix. $\uparrow$		FVD-V $\downarrow$	CLIP-V $\uparrow$	CLIP-F $\uparrow$	RotErr $\downarrow$	TransErr $\downarrow$
		Dynamic	Static
DaS [ 22 ]	49	494	1251	315.69	86.01	97.40	0.1549	0.2164
Go-with-the-Flow [ 11 ]	49	687	1277	296.30	87.44	96.78	0.1225	0.1109
ReCamMaster [ 4 ]	75	1073	1428	233.70	88.06	97.39	0.1665	0.1778
ArtiFixer-14B [ 14 ]	75	1128	1937	195.55	88.99	97.55	0.0780	0.0529

Table 1: Quantitative comparison on view synchronization, temporal consistency and camera accuracy on Multi-ViewBench videos. Metrics are defined in Sec. 4.2 .

Table 2: Quantitative comparison on VBench [ 21 ] metrics .

Figure 2: Qualitative comparison on a Multi-ViewBench example with an Arc-right trajectory.

Variant		View Synchronization			Temporal Consistency
		Mat. Pix. $\uparrow$	FVD-V $\downarrow$	CLIP-V $\uparrow$	CLIP-F $\uparrow$
Noise	standard	222	518.77	88.76	97.34
Noise	w/o whitening	208	468.39	88.53	96.92
	w/ whitening	267	461.44	91.05	97.61
Conditioning	+none (I2V)	224	830.00	87.53	97.80
	+render view	231	574.50	89.34	97.59

Table 4: Ablations. Visual-quality and view-synchronization metrics on various factors.

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Field	Range	Requirement or meaning
Gates (all must be true)
is_single_continuous_shot	bool	No cuts or transitions.
is_real_time_playback	bool	No time-lapse, hyper-lapse, or slow motion.
is_physically_plausible	bool	No VFX blends, text overlays, or screen-in-screen.
is_motion_blur_acceptable	bool	No motion blur severe enough to destroy structure.
is_focal_blur_acceptable	bool	Not excessively out of focus.

Appendix

Table 5: Stage-1 judgement schema. The model must return every field. Gates are hard requirements: a clip is admissible only if all six are true. The composition bucket defines the standard / complex split, and the semantic scores feed the richness index of Sec. A.1.3 .

#	Stage	Surviving	Removed
	Stage-1 judgements available	7,561
1	Gate pass (all six gates true)	6,617	944 gate failures
2	Landscape (width $>$ height)	5,973	644 portrait or square
3	De-duplication (unique clips)	4,541	1,432 copies of 1,197 clips
4	Moving camera body	2,231	2,310 static-source
5	Optical-effect removal	2,227	4 optical-effect

Appendix

Table 6: Curation funnel. Counts at the time the benchmark was frozen, when 7,561 of the 9,194 corpus clips had been scored. De-duplication runs after the gate and landscape filters but before static-source classification; see Sec. A.1.5 for why the order matters.

	Standard	Complex
Composition bucket	simple	complex
Candidates in pool	404	1,823
Selection	top 100 by $\rho$	balance to 1,000, then top 100 by $\rho$
$\rho$ range	24.0–64.0	64.0–100.0
$\rho$ mean	30.9	71.2
$\rho$ median	32.0	64.0

Appendix

Table 7: The two released splits of Multi-ViewBench. Both hold 100 clips, are disjoint, and are drawn from the 2,227-clip pool of Table 6 . Richness

\rho

is defined in Eq. 20 . Attribute rows give the distribution over the 100 clips.

Panel of Figure 3 — Figure 3: Schematic of the six synthesized evaluation trajectories ; Every trajectory is a camera-local SE(3) delta $\Delta_{t}$ composed after the source camera’s pose at each frame (Eq. 21 ), so all six depart from the same source pose ( Start ) at $t=0$ and diverge from it over the clip. Arc left/right (violet) sweep the camera around a pivot ahead of it in the local horizontal (right–forward) plane; Dolly in/out (orange) dolly along the local forward axis toward/away from that pivot; Pedestal-up-Tilt-down and Pedestal-down-Tilt-up (blue) shift the camera along its local down axis while tilting about its local right axis so the same pivot stays centred in frame.

	4D representation (NoPo4D)	Noise rasterization	Whitening	Video generation (WAN2.2-14B)
				DiT	VAE decoder	Total
Compute time (sec.)	4.18	6.44	0.53	23.97 / step	4.60	1203.1

Appendix

Table 8: Compute time breakdown for the four main components of SyncVid. Times are reported in seconds per input clip with 75 frames at 480

\times

832 resolution on an Nvidia H100 GPU. The DiT time is reported per denoising step.

Panel of Figure 4 — Figure 4: Qualitative comparisons under a Dolly-out camera trajectory. For each example, six equally spaced frames are shown for the source video and each method’s generated reshoot.

Panel of Figure 5 — Figure 5: Qualitative comparisons under an Arc-right camera trajectory. For each example, six equally spaced frames are shown for the source video and each method’s generated reshoot.

Panel of Figure 6 — Figure 6: Qualitative comparisons under an Arc-left camera trajectory. For each example, six equally spaced frames are shown for the source video and each method’s generated reshoot.

Panel of Figure 7 — Figure 7: Failure examples. Each example shows six equally spaced source frames in the first row, followed by the corresponding generated frames. The top example follows Arc-left and the bottom example shows Dolly-out trajectory.

Multi-View Video Generation

Multi-view video generation creates synchronized, viewpoint-consistent videos for controllable scene synthesis, reconstruction, and simulation.

See all 57 papers

AnyView: Synthesizing Any Novel View in Dynamic Scenes
Jan 23, 2026Basile Van Hoorick, Dian Chen, Shun Iwase +7Multi-View Consistency Camera-Conditioned Video Generation
Toyota Research Institute, CA, USA · Amazon Web Services, CA, USA
MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing
Jul 6, 2026Gal Fiebelman, Hadar Averbuch-Elor, Sagie BenaimMulti-View Consistency Video Diffusion Models
The Hebrew University of Jerusalem · Cornell University
Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation
Jul 2, 2026Long Vu, Tan Ngo, Animesh Karnewar +5Camera-Controlled Video Generation Video Diffusion Models
Qualcomm AI Research · Trinity College Dublin, Ireland

Jan 23, 2026J/K move · Enter open · S save

AnyView: Synthesizing Any Novel View in Dynamic Scenes

Basile Van Hoorick, Dian Chen, Shun Iwase, Pavel Tokmakov+6

Toyota Research Institute, CA, USA · Amazon Web Services, CA, USA

Multi-View Consistency Camera-Conditioned Video Generation Video Diffusion Models Multi-View Video Generation Dynamic Novel View Synthesis Temporal Consistency in Video Generation+1

Open paper AskPDF arXiv

Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce

\textbf{AnyView}

, a diffusion-based video generation framework for

\textit{dynamic view synthesis}

with minimal inductive biases or geometric assumptions. We leverage multiple data sources with various levels of supervision, including monocular (2D), multi-view static (3D) and multi-view dynamic (4D) datasets, to train a generalist spatiotemporal implicit representation capable of producing zero-shot novel videos from arbitrary camera locations and trajectories. We evaluate AnyView on standard benchmarks, showing competitive results with the current state of the art, and propose

\textbf{AnyViewBench}

, a challenging new benchmark tailored towards

\textit{extreme}

dynamic view synthesis in diverse real-world scenarios. In this more dramatic setting, we find that most baselines drastically degrade in performance, as they require significant overlap between viewpoints, while AnyView maintains the ability to produce realistic, plausible, and spatiotemporally consistent videos when prompted from

\textit{any}

viewpoint. Results, data, code, and models can be viewed at: https://tri-ml.github.io/AnyView/

Abstract

Multi-View Video Generation

Explore similar work

AnyView: Synthesizing Any Novel View in Dynamic Scenes

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation