DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
hub
Shape of motion: 4d reconstruc- tion from a single video
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
Proposes GPS representation for articulated parts, uses VR to annotate 41K frames across 234 objects, trains an RGB-D model, and achieves 73% success in heuristic manipulation policies on 9 objects.
RoDyGS separates static and dynamic elements in monocular videos using Gaussian splatting with regularization and introduces the Kubric-MRig benchmark for pose-free dynamic novel view synthesis.
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
PhysGaia is a physics-aware benchmark for dynamic novel view synthesis that supplies scenes with multi-body interactions, diverse materials, and ground-truth particle trajectories generated by material-specific physics solvers.
By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.
citing papers explorer
-
DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images
DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
-
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
-
Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
-
Revisiting Articulated Parts Perception in Robot Manipulation
Proposes GPS representation for articulated parts, uses VR to annotate 41K frames across 234 objects, trains an RGB-D model, and achieves 73% success in heuristic manipulation policies on 9 objects.
-
RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos
RoDyGS separates static and dynamic elements in monocular videos using Gaussian splatting with regularization and introduces the Kubric-MRig benchmark for pose-free dynamic novel view synthesis.
-
Geometry-aware 4D Video Generation for Robot Manipulation
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
-
PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis
PhysGaia is a physics-aware benchmark for dynamic novel view synthesis that supplies scenes with multi-body interactions, diverse materials, and ground-truth particle trajectories generated by material-specific physics solvers.
-
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.
-
A Survey on 3D Gaussian Splatting
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.
- Functionalization via Structure Completion and Motion Rectification