Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
3dtrajmaster: Mastering 3d trajectory for multi-entity motion in video generation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 7years
2026 7roles
background 1polarities
background 1representative citing papers
A self-supervised framework learns implicit 3D physics by lifting V-JEPA features into voxels and performing volumetric feature advection conditioned on actions.
T2Mo generates controllable dynamic 3D shapes by conditioning on both text semantics and 3D trajectories with a shape-grounded embedding for arbitrary inputs.
Introduces mesh tokenization to condition DiT-based video diffusion models directly on 3D human meshes for motion control without 2D rendering.
AnchorWorld proposes a simulation framework that adds exogenous viewpoint supervision for full-body grounding and anchor-view text customization for dynamic world evolution in egocentric settings.
Real2SAM2Real uses 3D caches from lifting models as complementary context for video diffusion models to enable precise decoupled control over camera trajectories and multi-entity motions while maintaining spatiotemporal consistency.
citing papers explorer
-
Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
-
Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection
A self-supervised framework learns implicit 3D physics by lifting V-JEPA features into voxels and performing volumetric feature advection conditioned on actions.
-
Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
T2Mo generates controllable dynamic 3D shapes by conditioning on both text semantics and 3D trajectories with a shape-grounded embedding for arbitrary inputs.
-
Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization
Introduces mesh tokenization to condition DiT-based video diffusion models directly on 3D human meshes for motion control without 2D rendering.
-
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
AnchorWorld proposes a simulation framework that adds exogenous viewpoint supervision for full-body grounding and anchor-view text customization for dynamic world evolution in egocentric settings.
-
Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion
Real2SAM2Real uses 3D caches from lifting models as complementary context for video diffusion models to enable precise decoupled control over camera trajectories and multi-entity motions while maintaining spatiotemporal consistency.
- HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control