Stable Virtual Camera: Generative View Synthesis with Diffusion Models
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NWZYA6QErecord.jsonopen to challenge →
read the original abstract
We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene, given any number of input views and target cameras. Existing works struggle to generate either large viewpoint changes or temporally smooth samples, while relying on specific task configurations. Our approach overcomes these limitations through simple model design, optimized training recipe, and flexible sampling strategy that generalize across view synthesis tasks at test time. As a result, our samples maintain high consistency without requiring additional 3D representation-based distillation, thus streamlining view synthesis in the wild. Furthermore, we show that our method can generate high-quality videos lasting up to half a minute with seamless loop closure. Extensive benchmarking demonstrates that Seva outperforms existing methods across different datasets and settings. Project page with code and model: https://stable-virtual-camera.github.io/.
This paper has not been read by Pith yet.
Forward citations
Cited by 20 Pith papers
-
Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
NeuWorld uses a transformer VAE to learn compact Neural Implicit Scenes from sparse posed frames and a diffusion transformer to evolve them conditioned on camera trajectories for consistent interactive exploration.
-
DeltaCam: Differential Intrinsic Camera Modeling for Video Generation
DeltaCam models relative changes in camera intrinsics via Δ-parameterized neural adaptors in video diffusion models trained on synthetic data to enable controllable generation and real-world transfer.
-
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
3D-Belief maintains and updates explicit 3D beliefs about partially observed environments to enable multi-hypothesis imagination and improved performance on embodied tasks.
-
Geometrically Consistent Multi-View Scene Generation from Freehand Sketches
A framework generates consistent multi-view scenes from one freehand sketch via a ~9k-sample dataset, Parallel Camera-Aware Attention Adapters, and Sparse Correspondence Supervision Loss, outperforming baselines in re...
-
PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation
PerpetualWonder introduces a closed-loop generative simulator with a unified physical-visual representation for long-horizon action-conditioned 4D scene generation from one image.
-
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
A viewpoint-conditioned diffusion model generates stereo image pairs from monocular input in a canonical rectified space without using depth or explicit warping.
-
GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion
GeoFace generates consistent multi-view face images and 3D geometry from one input via a dual-stream diffusion framework with geometry-guided attention alignment.
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
Latent Spatial Memory for Video World Models
Mirage stores and queries 3D scene information in diffusion latent space via depth-guided lifting and warping, yielding 10.57× faster generation and 55× smaller memory than explicit RGB point-cloud baselines while rea...
-
Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
COVRAG improves long-horizon geometric consistency in autoregressive video generation via coverage-maximizing retrieval on lightweight depth-based 3D memory evidence.
-
RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
RayDer is a unified transformer backbone for self-supervised static-scene novel view synthesis that absorbs dynamic content as a nuisance factor and shows power-law scaling with data and compute while matching supervi...
-
Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
A feed-forward model aligns ground and satellite features to predict Gaussian splats for improved novel-view synthesis on georeferenced outdoor scenes.
-
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Decouples semantic and spatial tokens in NVS transformers to resolve representation ambiguity, yielding consistent gains with near-zero added latency.
-
Vista4D: Video Reshooting with 4D Point Clouds
Vista4D re-synthesizes dynamic videos from new viewpoints by grounding them in a 4D point cloud built with static segmentation and multiview training.
-
Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.
-
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
WorldPlay uses dual action representation, reconstituted context memory, and context forcing distillation to produce consistent 720p streaming video at 24 FPS for interactive world modeling.
-
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
VolFill uses a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into latent space and a latent Diffusion Transformer to denoise complete scenes, conditioned on geometry foundation models, ou...
-
Unified 3D Scene Understanding Through Physical World Modeling
A probabilistic graphical model called 3WM unifies 3D vision tasks into one system that performs them zero-shot by selecting different inference pathways through multimodal scene nodes.
-
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Introduces a robustness benchmark for multiview 3D consistency and COLMAP-based metrics that better detect hallucinations in 3D foundation models than existing neural metrics.
-
ViPE: Video Pose Engine for 3D Geometric Perception
ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.