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 supervised methods in zero-shot settings.
hub
Novel view synthesis with diffusion models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
representative citing papers
PanoWorld adds depth consistency and trajectory consistency losses plus spherical adaptations to a pre-trained video model, plus a new PanoGeo dataset, to produce geometry-consistent 360 video.
Kinematics-GS reparameterizes Gaussian shapes along motion trajectories with a kinematic prior to reconstruct dynamic 3D scenes from blurry monocular videos by separating dynamic and static components and using coarse-to-fine optimization.
A multi-view diffusion model generates consistent novel views from sparse images to enable fast 3D scene reconstruction.
Moment-matched GMM kernels in DDIM yield lower FID and higher IS than Gaussian kernels at small sampling steps on CelebA-HQ, FFHQ, ImageNet, and Stable Diffusion tasks.
SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
A two-stage method trains NeRF latents then a diffusion prior to sample posteriors for 3D reconstruction from varied observations including single-view, multi-view, noisy, sparse pixels, and sparse depth.
3DTV proposes a feedforward network for real-time sparse-view interpolation using Delaunay triplet selection and a pose-aware coarse-to-fine depth module, outperforming real-time baselines without scene-specific optimization.
KFC-W is a self-supervised 3D-aware video model trained on videos and multiview internet photos that produces geometrically consistent interpolations between unposed input images without any 3D annotations.
Empirical study finds that object pose and shape estimation followed by antipodal grasp sampling outperforms end-to-end grasp synthesis for 7-DoF parallel-jaw grasping from single-view RGB-D input.
citing papers explorer
-
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 supervised methods in zero-shot settings.
-
PanoWorld: Geometry-Consistent Panoramic Video World Modeling
PanoWorld adds depth consistency and trajectory consistency losses plus spherical adaptations to a pre-trained video model, plus a new PanoGeo dataset, to produce geometry-consistent 360 video.
-
Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
Kinematics-GS reparameterizes Gaussian shapes along motion trajectories with a kinematic prior to reconstruct dynamic 3D scenes from blurry monocular videos by separating dynamic and static components and using coarse-to-fine optimization.
-
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
A multi-view diffusion model generates consistent novel views from sparse images to enable fast 3D scene reconstruction.
-
Improved DDIM Sampling with Moment Matching Gaussian Mixtures
Moment-matched GMM kernels in DDIM yield lower FID and higher IS than Gaussian kernels at small sampling steps on CelebA-HQ, FFHQ, ImageNet, and Stable Diffusion tasks.
-
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.
-
Shap-E: Generating Conditional 3D Implicit Functions
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
-
Predicting 3D structure by latent posterior sampling
A two-stage method trains NeRF latents then a diffusion prior to sample posteriors for 3D reconstruction from varied observations including single-view, multi-view, noisy, sparse pixels, and sparse depth.
-
3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis
3DTV proposes a feedforward network for real-time sparse-view interpolation using Delaunay triplet selection and a pose-aware coarse-to-fine depth module, outperforming real-time baselines without scene-specific optimization.
-
KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos
KFC-W is a self-supervised 3D-aware video model trained on videos and multiview internet photos that produces geometrically consistent interpolations between unposed input images without any 3D annotations.
-
Object Pose and Shape Estimation for Grasping: Does it Work?
Empirical study finds that object pose and shape estimation followed by antipodal grasp sampling outperforms end-to-end grasp synthesis for 7-DoF parallel-jaw grasping from single-view RGB-D input.