No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views

a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.

FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views

Fast3R dramatically improves 3D reconstruction speed by processing up to 1500 images in a single forward pass.

All-in-One Video Creation and Editing

Project page of the paper: A Distractor-Aware Memory for Visual Object Tracking with SAM2

Abstract Recovering high-quality 3D scenes from a single RGB image is a challenging task in computer graphics. Current methods often struggle with domain-specific limitations or low-quality object ge...

SOCIAL MEDIA DESCRIPTION TAG TAG

Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction, self-calibrating gs

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

Flow Based Video Generative Foundation Models

A unified framework for scene completion that reconstructs and completes missing parts of casually captured scenes.

SOCIAL MEDIA DESCRIPTION TAG TAG

Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion

DiffVSR