Flex3D features a two-stage process that generates high-quality 3D assets from a single image or text prompt. This technology represents the latest advancements in the field of 3D reconstruction, significantly improving the efficiency and quality of 3D content generation. Flex3D is developed with support from Meta, and the team has a strong background in 3D reconstruction and computer vision.

GameNGen is a fully neural model-driven game engine capable of real-time interaction with complex environments while maintaining high quality over extended trajectories. It can interactively simulate the classic game 'DOOM' at over 20 frames per second, with its next-frame prediction achieving a PSNR of 29.4, comparable to lossy JPEG compression. Human evaluators only slightly outperform random chance in distinguishing between game clips and simulated clips. GameNGen is trained through two phases: (1) an RL-agent learns to play the game and records the actions and observations from the training sessions, which become the training data for the generative model; (2) a diffusion model is trained to predict the next frame, conditioned on the past actions and observation sequences. Conditional enhancement allows for stable autoregressive generation over long trajectories.

EgoGaussian is an advanced 3D scene reconstruction and dynamic object tracking technology. It can reconstruct 3D scenes and track the movement of objects dynamically using only RGB first-person perspective input. This technology leverages the unique discrete properties of Gaussian scattering to segment dynamic interactions from the background. Through a piece-wise online learning process, it utilizes the dynamic characteristics of human activities to reconstruct the evolution of the scene in chronological order and track the movement of rigid objects. EgoGaussian outperforms previous NeRF and dynamic Gaussian methods in wild video challenges and delivers exceptional quality in reconstructed models.

GaussianCube is an innovative 3D radiance representation method that significantly advances 3D generative modeling through its structured and explicit representation. This technology achieves high-precision fitting by utilizing a novel density-constrained Gaussian fitting algorithm and optimal transport methods, rearranging Gaussian functions onto a predefined voxel grid. Compared to traditional implicit feature decoders or spatially unstructured radiance representations, GaussianCube boasts fewer parameters and higher quality, making 3D generative modeling more accessible.

Developed by a team from Tsinghua University, Unique3D is a technology that can generate high-fidelity textured 3D mesh models from a single image. This technology has significant implications for image processing and 3D modeling, enabling users to quickly convert 2D images into 3D models, providing powerful technical support for game development, animation production, and virtual reality.

VastGaussian is an open-source project for 3D scene reconstruction that leverages 3D Gaussians to model the geometric and appearance information of large-scale scenes. This project is an implementation from scratch and may contain some errors, but it offers a new perspective for the field of 3D scene reconstruction. Key advantages include its ability to process large datasets and the improvements made to the original 3DGS project, enhancing its clarity and usability.

PhysDreamer is a method based on physics, which endows静态 3D objects with interactive dynamics by utilizing the object dynamics prior learned from video generation models. This approach allows for the simulation of realistic responses to novel interactions (such as external forces or agent operations) in the absence of real physical property data of objects. PhysDreamer promotes the development of more engaging and realistic virtual experiences through user studies to evaluate the realism of synthetic interactions.

Interactive3D is an advanced 3D generation model that provides users with precise control capabilities through interactive design. The model utilizes a two-stage cascading structure, employing different 3D representation methods, allowing users to modify and guide at any intermediate step of the generation process. Its significance lies in the ability to achieve fine control over the 3D model generation process, thereby creating high-quality 3D models that meet specific requirements.

DexCap is a portable hand motion capture system that combines holography and electromagnetic field technology to provide accurate and occlusion-resistant wrist and finger motion tracking. It collects data by 3D observing the environment. The DexIL algorithm leverages inverse kinematics and point cloud-based imitation learning to directly train dexterous robotic hand skills from human hand movement data. The system supports optional human-in-the-loop calibration mechanisms, enabling the robotic hand to replicate human movements and further improve its performance based on human hand actions.

MakerLab is an online platform offering a variety of 3D model design tools, including vase generators and sign customizers. Users can quickly and easily create personalized 3D models based on their own needs. The platform supports the use of templates for creation and provides an innovation playground where users can experiment with cutting-edge technologies like AI scanners. MakerLab is operated by BamBam Lab and aims to provide a space for users to freely create and share their ideas. Currently, the platform offers both free and paid services for users to choose according to their needs.

Flex3D features a two-stage process that generates high-quality 3D assets from a single image or text prompt. This technology represents the latest advancements in the field of 3D reconstruction, significantly improving the efficiency and quality of 3D content generation. Flex3D is developed with support from Meta, and the team has a strong background in 3D reconstruction and computer vision.

GameNGen is a fully neural model-driven game engine capable of real-time interaction with complex environments while maintaining high quality over extended trajectories. It can interactively simulate the classic game 'DOOM' at over 20 frames per second, with its next-frame prediction achieving a PSNR of 29.4, comparable to lossy JPEG compression. Human evaluators only slightly outperform random chance in distinguishing between game clips and simulated clips. GameNGen is trained through two phases: (1) an RL-agent learns to play the game and records the actions and observations from the training sessions, which become the training data for the generative model; (2) a diffusion model is trained to predict the next frame, conditioned on the past actions and observation sequences. Conditional enhancement allows for stable autoregressive generation over long trajectories.

This is a robotic table tennis agent model developed by the Google DeepMind team. It utilizes deep learning technology to achieve competitive performance against amateur human players in table tennis matches. The significance of this technology lies in its advancement of robotics for high-speed movement, real-time precise decision-making, and strategic planning, while providing a valuable benchmark for direct competition between robots and humans.

SoulWanderer is a visual novel game designed by Yajing Pang. The narrative follows two sisters who are forced to land on an unknown planet due to a spaceship accident. They explore this world, meet various characters, discover new realms, learn new knowledge, and ultimately reveal a secret. The storyline is captivating and is complemented by beautiful illustrations, philosophical dialogues, reflections, and accolades. Players can read the entire story in under 15 minutes, with the text comprising less than 10,000 words. This game is perfect for those who enjoy visual novels and the thrill of exploration.

what beats rock? is an online logic game designed to test players' logical thinking and problem-solving skills. The game presents questions like 'What beats rock?' prompting players to think critically and find solutions. It not only exercises the brain but also offers a fun and engaging entertainment experience.

EgoGaussian is an advanced 3D scene reconstruction and dynamic object tracking technology. It can reconstruct 3D scenes and track the movement of objects dynamically using only RGB first-person perspective input. This technology leverages the unique discrete properties of Gaussian scattering to segment dynamic interactions from the background. Through a piece-wise online learning process, it utilizes the dynamic characteristics of human activities to reconstruct the evolution of the scene in chronological order and track the movement of rigid objects. EgoGaussian outperforms previous NeRF and dynamic Gaussian methods in wild video challenges and delivers exceptional quality in reconstructed models.

GaussianCube is an innovative 3D radiance representation method that significantly advances 3D generative modeling through its structured and explicit representation. This technology achieves high-precision fitting by utilizing a novel density-constrained Gaussian fitting algorithm and optimal transport methods, rearranging Gaussian functions onto a predefined voxel grid. Compared to traditional implicit feature decoders or spatially unstructured radiance representations, GaussianCube boasts fewer parameters and higher quality, making 3D generative modeling more accessible.

Developed by a team from Tsinghua University, Unique3D is a technology that can generate high-fidelity textured 3D mesh models from a single image. This technology has significant implications for image processing and 3D modeling, enabling users to quickly convert 2D images into 3D models, providing powerful technical support for game development, animation production, and virtual reality.