Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
3d scene prompting for scene-consistent camera-controllable video generation
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.CV 8years
2026 8roles
extension 1polarities
extend 1representative citing papers
C4G introduces compact timestamp-conditioned Gaussian query tokens that aggregate full temporal context to decode 3D Gaussians with timestamp-modulated positions for feed-forward 4D reconstruction from monocular video, plus a diffusion-based rendering module and extension to 4D feature fields.
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.
DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
E³C is a video diffusion model that disentangles persistent 3D scene structure via point-cloud memory from human dynamics via ego-exo pose controls for improved egocentric video generation on the Nymeria dataset.
MVTrack4Gen uses multi-view point tracking as geometric and motion supervision for camera-conditioning-only novel-view video diffusion models to improve consistency.
Aligning flow-matching assembly networks to frozen 3D encoder topology via cosine and CKA losses speeds training up to 6.9× and improves in- and out-of-distribution assembly accuracy with zero inference cost.
citing papers explorer
-
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
-
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
C4G introduces compact timestamp-conditioned Gaussian query tokens that aggregate full temporal context to decode 3D Gaussians with timestamp-modulated positions for feed-forward 4D reconstruction from monocular video, plus a diffusion-based rendering module and extension to 4D feature fields.
-
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.
-
DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis
DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.
-
Echo-Memory: A Controlled Study of Memory in Action World Models
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
-
E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control
E³C is a video diffusion model that disentangles persistent 3D scene structure via point-cloud memory from human dynamics via ego-exo pose controls for improved egocentric video generation on the Nymeria dataset.
-
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
MVTrack4Gen uses multi-view point tracking as geometric and motion supervision for camera-conditioning-only novel-view video diffusion models to improve consistency.
-
TORA: Topological Representation Alignment for 3D Shape Assembly
Aligning flow-matching assembly networks to frozen 3D encoder topology via cosine and CKA losses speeds training up to 6.9× and improves in- and out-of-distribution assembly accuracy with zero inference cost.