IEEE

3D Gaussian Splatting as a New Era: A Survey

Abstract: 3D Gaussian Splatting (3D-GS) has emerged as a significant advancement in the field of computer graphics and 3D vision, offering explicit scene representation and novel view synthesis ...
GitHub

3D GAN Inversion with Pose Optimization

With the recent advances in NeRF-based 3D aware GANs quality, projecting an image into the latent space of these 3D-aware GANs has a natural advantage over 2D GAN inversion: not only does it allow ...
IEEE

Joint 3D Proposal Generation and Object Detection from View Aggregation

Abstract: We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate ...
www.cs.cmu.edu

3D Object Manipulation in a Single Photograph using Stock 3D Models

We were interviewed about our work by WESA (the NPR radio station in Pittsburgh), and we were featured live on the local radio station KQV 1410 AM. Abstract Photo-editing software restricts the ...
GitHub

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.