Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.
hub
Cameractrl ii: Dynamic scene exploration via camera-controlled video diffusion models
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
CT-1 transfers spatial reasoning from vision-language models to estimate camera trajectories, which are then used in a video diffusion model with wavelet regularization to produce controllable videos, claiming 25.7% better accuracy than prior methods.
OmniCamera disentangles video content and camera motion for multi-task generation with arbitrary camera control via the OmniCAM hybrid dataset and Dual-level Curriculum Co-Training.
GimbalDiffusion lets text-to-video models follow absolute, gravity-aligned camera rotations by training on random crops from 360° video with forward-facing captions.
OrthoMotion disentangles camera and subject motion in video generation by splitting attention into algebraically complementary geometric (RoPE rotation) and semantic (gated value) channels driven to orthogonality by a decoupling regularizer.
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
TriMotion is a modality-agnostic framework that maps video, pose, and text descriptions of the same camera trajectory into a shared motion embedding space, trained with a new triplet dataset and latent consistency objective, to produce videos that follow the target trajectory.
ParaScale extracts a gauge-invariant Parallax Number from a reference video and re-realizes the same parallax against the target scene's depth map to achieve scale-calibrated camera motion transfer.
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 reaching SOTA on WorldScore.
Auteur formalizes human-centric camera framing as a DSL, uses a fine-tuned MLLM to map text and motion to DSL keyframes, and interpolates them into trajectories for video generators.
StreetNVS presents a multi-sensor conditioned video diffusion framework for street-view novel view synthesis that outperforms baselines with sparse LiDAR and handles extreme out-of-trajectory paths on the Waymo dataset.
CameraNoise embeds camera motion into the noise space of video diffusion via Geometry-guided Reprojection Flow and noise warping to achieve faithful trajectory control while preserving the diffusion prior.
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
Pantheon360 introduces a controllable 360° video diffusion framework that uses an explicit 3D cache from sparse inputs to enforce geometric consistency for digital twin generation.
citing papers explorer
-
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.
-
CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation
CT-1 transfers spatial reasoning from vision-language models to estimate camera trajectories, which are then used in a video diffusion model with wavelet regularization to produce controllable videos, claiming 25.7% better accuracy than prior methods.
-
OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
OmniCamera disentangles video content and camera motion for multi-task generation with arbitrary camera control via the OmniCAM hybrid dataset and Dual-level Curriculum Co-Training.
-
GimbalDiffusion: Gravity-Aware Camera Control for Video Generation
GimbalDiffusion lets text-to-video models follow absolute, gravity-aligned camera rotations by training on random crops from 360° video with forward-facing captions.
-
OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention
OrthoMotion disentangles camera and subject motion in video generation by splitting attention into algebraically complementary geometric (RoPE rotation) and semantic (gated value) channels driven to orthogonality by a decoupling regularizer.
-
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.
-
TriMotion: Modality-Agnostic Camera Control for Video Generation
TriMotion is a modality-agnostic framework that maps video, pose, and text descriptions of the same camera trajectory into a shared motion embedding space, trained with a new triplet dataset and latent consistency objective, to produce videos that follow the target trajectory.
-
ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number
ParaScale extracts a gauge-invariant Parallax Number from a reference video and re-realizes the same parallax against the target scene's depth map to achieve scale-calibrated camera motion transfer.
-
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 reaching SOTA on WorldScore.
-
Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
Auteur formalizes human-centric camera framing as a DSL, uses a fine-tuned MLLM to map text and motion to DSL keyframes, and interpolates them into trajectories for video generators.
-
Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis
StreetNVS presents a multi-sensor conditioned video diffusion framework for street-view novel view synthesis that outperforms baselines with sparse LiDAR and handles extreme out-of-trajectory paths on the Waymo dataset.
-
CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
CameraNoise embeds camera motion into the noise space of video diffusion via Geometry-guided Reprojection Flow and noise warping to achieve faithful trajectory control while preserving the diffusion prior.
-
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
-
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
-
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
-
Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\deg} Video Diffusion
Pantheon360 introduces a controllable 360° video diffusion framework that uses an explicit 3D cache from sparse inputs to enforce geometric consistency for digital twin generation.