Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
Redirector: Creating any-length video retakes with rotary camera encoding
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 6years
2026 6roles
background 1polarities
background 1representative citing papers
A synthetic data pipeline and fine-tuned video model enable generative editing to move object 3D trajectories in videos while keeping relative motion.
A single indoor panorama is converted end-to-end into an explorable 3D Gaussian scene via joint multi-view panoramic diffusion and a latent feature adapter that bypasses RGB re-encoding.
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
SierpinskiCam adds Sierpinski dome texture cues and negative-RoPE reference video conditioning to geometry-guided video diffusion to improve camera controllability and consistency in video retaking.
MVTrack4Gen uses multi-view point tracking as geometric and motion supervision for camera-conditioning-only novel-view video diffusion models to improve consistency.
citing papers explorer
-
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
-
TrajectoryMover: Generative Movement of Object Trajectories in Videos
A synthetic data pipeline and fine-tuned video model enable generative editing to move object 3D trajectories in videos while keeping relative motion.
-
Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences
A single indoor panorama is converted end-to-end into an explorable 3D Gaussian scene via joint multi-view panoramic diffusion and a latent feature adapter that bypasses RGB re-encoding.
-
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
-
SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
SierpinskiCam adds Sierpinski dome texture cues and negative-RoPE reference video conditioning to geometry-guided video diffusion to improve camera controllability and consistency in video retaking.
-
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.