World Tracing introduces a multi-layer pixel-aligned 3D point representation instantiated via a diffusion transformer (WT-DiT) trained with pixel-space flow matching to jointly reconstruct visible surfaces and generate occluded geometry.
LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5representative citing papers
CHOIR reconstructs articulated hand motion, object shape with 6D pose, and contact from monocular videos via coarse initialization, generative spatial rectification, and contact-aware joint optimization.
RGSUD achieves SOTA unsupervised deraining by using IQA-based reward recycling and self-reinforcement to constrain optimization and improve pseudo-paired data quality.
GlowGS improves 3D Gaussian Splatting in nighttime glow scenes via semantic feature generation from diffusion models and novel-view semantic learning with vision foundation models.
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
citing papers explorer
-
World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible
World Tracing introduces a multi-layer pixel-aligned 3D point representation instantiated via a diffusion transformer (WT-DiT) trained with pixel-space flow matching to jointly reconstruct visible surfaces and generate occluded geometry.
-
CHOIR: Contact-aware 4D Hand-Object Interaction Reconstruction
CHOIR reconstructs articulated hand motion, object shape with 6D pose, and contact from monocular videos via coarse initialization, generative spatial rectification, and contact-aware joint optimization.
-
Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
RGSUD achieves SOTA unsupervised deraining by using IQA-based reward recycling and self-reinforcement to constrain optimization and improve pseudo-paired data quality.
-
GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
GlowGS improves 3D Gaussian Splatting in nighttime glow scenes via semantic feature generation from diffusion models and novel-view semantic learning with vision foundation models.
-
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.