paulpanwang

POPE. Welcome to the project repository for POPE (Promptable Pose Estimation), a state-of-the-art technique for 6-DoF pose estimation of any object in any scene using a single reference.

Diff4Splat. [CVPR 2026] Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models.

Underwater-Image-De-Scattering. De-scattering and edge enhancing are critical procedures for underwater images which surfer from serious detail loss, color deviation and blurring. In this work, a novel method has been proposed to enhance contrast and edge of underwater images.

Cas6D. [3D Vision 2024] A new cascade framework named Cas6D for few-shot 6DoF pose estimation that is generalizable and uses only RGB images.

ID-Crafter. [CVPR 2026] Official implementation of VLM-Grounded Online RL for Compositional Multi-Subject Video Generation

Face_alignment. In face-related applications, the obtained face images often have different shapes. At this time, the face shape needs to be normalized. Face alignment is the process of normalizing two different shapes, placing one shape as close to the other as possible.

YOLO-Android. Java

Gen6DNeRF. Python

SPECK. SPECK——a lossless compression method for 3-D color images is proposed. First，the IIntKLT is applied to reduce the redundancies between the color components，so that the complete reversible transform is guaranteed，and then by using SPECK，the performance of coding is improved． The results of experimentation of standard testing color image，show that the new approach has an increase of 0. 1 bpp in lossless image compression，and in the case of complete reversible lossy compression，compared with JPEG2000，it at most has a increase of 0. 88 dB．

humancrafter. HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation