Technology peripherals
AI
'Black Wukong' real-life demonstration explodes, NVIDIA shows off light tracing technology
'Black Wukong' real-life demonstration explodes, NVIDIA shows off light tracing technology
After a year, "Black Wukong" is back and once again on the hot list.
#This time, in addition to the official release of a 6-minute live plot clip, NVIDIA also brought an 8-minute live trial clip.
What’s more important is that this is the first time that “Black Wukong” supports 4K RTX ON ray tracing NVIDIA DLSS technology.
#Netizens’ blood boiled instantly after watching it.
The first 4K light chasing DLSS
In 2020, Black Wukong was exposed for the first time, shocking the world.
In 2021, the test of UE5 will be shown, and the snowy ground scene processing will make netizens call the graphics card Crisis China Edition.
#In 2022, I went directly to NVIDIA 4K RTX ON.
Let’s compare the scene where Wukong turns into a golden cicada at the beginning. This year’s wing modeling and flying movements are obviously more textured than the 2020 version.
#With the blessing of light chasing, different positions of Jin Chan’s body will also show different details based on different lighting angles, making it appear more realistic and natural.
Clearly, AI technology and ray tracing technology are changing the way we game and create.
From a technical point of view, ray tracing and DLSS have become standard equipment for producing AAA game masterpieces.
The reason why "Black Wukong" allows players to experience such an immersive fantasy world of Chinese mythology is because of its powerful ray tracing and NVIDIA DLSS , all powered by GeForce RTX technology.
NVIDIA RTX is at the forefront of the current revolution in gaming, the fastest, most advanced platform for cutting-edge applications and games.
If players use a GeForce RTX-powered PC and optimize it with the latest Game Ready driver, they will get the most powerful performance and the smoothest gaming experience experience and the highest fidelity ray tracing effects.
A milestone that subverts the gaming industry
Next, let’s introduce ray tracing and DLSS in detail.
On August 14, 2018, SIGGRAPH, the top computer graphics conference, was held in Vancouver. NVIDIA officially launched the world's first new graphics card family that supports real-time ray tracing technology. NVIDIA Quadro RTX.
On August 21, NVIDIA released a new generation of graphics cards based on the Turing architecture: GeForce 2080Ti, GeForce 2080 and GeForce 2070. Since then, GPU has opened up a new world of ray tracing for games.
#Real-time ray tracing technology and DLSS technology can definitely be regarded as milestone disruptions.
1. Ray tracing technology
Ray tracing is A graphics rendering method that simulates the physical properties of light.
#Before the advent of ray tracing, the traditional method was raster rendering.
Assume there is a room and a light source. From the inside of the room, give each surface a plane texture, and make each surface brighter or darker according to the position of the light source. First, Calculate the coordinate transformation (matrix transformation, perspective, etc.) of the object (room) corresponding to the polygon or triangle vertices on the screen, then fill the texture within the polygon or triangle, and simultaneously calculate the color of each pixel in the room, thereby generating a fairly realistic 3D Room.
The principle of ray tracing is to track the propagation behavior of each ray of light and calculate the effect of each ray of ray on our human eyes. The contribution value of the observation, that is, the color value. Rendered using ray tracing technology, the emitted light bounces around the scene just like it would in the real world, so it looks more realistic. It calculates where the light intersects the room and how much it should reflect, how the light passes through the virtual camera's lens, and finally, determines how the camera's image should appear on your screen.
Calculate and simulate to obtain information such as the color of each pixel projected onto the screen.
#Ray tracing is the reverse tracing of light from the camera (eye) to capture the various effects of light reflection.
Rasterization (left) and ray tracing (right)
In the game, a specialized light tracing (RT) core is used to simulate the physical changes of light in the game scene.
It can achieve physically accurate shadows, reflections and refractions, and global illumination in virtual game scenes. , making objects in the game more realistic.
#For example, the light and shadow changes in Black Wukong’s demonstration.
Also scenes such as flames, smoke and explosions look more realistic, making people feel like they are there It feels like it’s all the effect of light chasing.
#########In fact, the algorithm of ray tracing technology was proposed by Turner Whitted as early as 1979. Why did it take so many years to start using this technology for light rendering? This is because the amount of calculation required is too large. ##################In order to ensure the huge computing power demand, NVIDIA has an RT CORE in each SM unit in the Turing architecture, specifically for ray tracing services. The working principle of RT CORE is the hierarchical bounding box traversal algorithm: BVH (Bounding Volume Hierarchy Traversal). ##################For example, the rendering object is a rabbit. To calculate the interaction between a light ray and the rabbit itself, divide the space where the rabbit is located into N bounding boxes and calculate the light rays. Which bounding box does it intersect with? If yes, then divide the bounding box into N smaller bounding boxes and calculate the intersection again. Repeat this until you find the bounding box where the triangle that intersects with the light is located, and then perform the calculation on this triangle. Final render. #########
The BVH algorithm can greatly reduce the number of triangles that need to be traversed to calculate the nearest intersection point of each ray, and it only needs to be done once to use it for all rays, greatly Improved execution efficiency.
2.DLSS
Is the light chasing speed fast? , it needs another technology to be used together.
That’s NVIDIA Deep Learning Super Sampling (DLSS), a deep learning neural network that boosts frame rates and produces crisp images.
The full name of DLSS is Deep Learning Super Sampling, and the Chinese name is deep learning super sampling technology. It can use a low-resolution image (such as 1080P) to generate a high-resolution image (8K), and then shrink the 8K image back to 4K to obtain a super-sampled anti-aliasing (SSAA) image.
NVIDIA DLSS is the only super-resolution technology driven by AI. This advantage can bring the highest possible resolution to games. Up to 2x performance improvement.
#For example, in the foggy scene of Black Wukong, there was no unstable frame rate, mainly due to DLSS technology.
##DLSS is a new exclusive anti-aliasing technology launched by NVIDIA after TXAA, leveraging the power of deep learning and AI Features to train the GPU to render crisp game images.
The working principle of DLSS is image super-resolution technology, a function of optimizing images based on AI and deep learning. Through NVIDIA’s supercomputing, it continuously passes AI learns ultra-high-resolution game images and continuously restores low-resolution images to complete the details.
Because the supercomputer has huge computing power, it can slowly complete the details, improve the resolution, use deep convolutional neural network training, and finally output various An image with near-perfect detail and extremely high resolution.
The calculation process of DLSS is all completed in the Tensor Core core unit unique to the RTX graphics card, so it does not occupy The CUDA general-purpose computing unit of the graphics card avoids consuming the rendering performance of the graphics card and reducing the number of game frames.
#DLSS technology can be called a milestone in graphics card rendering. Because there is a rule in the graphics field, if you want better image quality, you must need better performance, and DLSS 2.0, a revolutionary technology, breaks this rule and can improve performance without affecting image quality. .
After turning on DLSS, the engine's rendering will run at a low resolution of 1/2 to 1/4 pixels. More than half of the pixel-level calculations are omitted. Pixel-level calculations are very time-consuming and performance-consuming. Generally speaking, 3A masterpieces with better graphics consume more rendering performance, and the more rendering performance becomes a bottleneck, while DLSS will provide greater acceleration.
There is no need to preset ultra-high-definition images in the game. As long as DLSS technology is used, the super-computing pre-calculated model built into the driver is enabled, and you can play The game will call the DLSS function when it is turned on.
What’s really special about DLSS is that it is the first AI algorithm to simultaneously generate stable images, yet Dither artifacts. Every game captures high-quality image sequences, avoiding the high cost of real-time rendering, and games render very quickly.
It is also the only picture scaling technology that can utilize deep learning neural networks to ensure that image quality is comparable to native resolution. Without AI-powered scaling technology, upscaled images can produce unsightly artifacts such as motion artifacts, flickering, and dull, blurry textures.
With the help of DLSS technology, the image quality can be improved first. Through advanced time feedback technology, clearer image details can be achieved while improving stability between frames.
Image captured at 1080p resolution using DLSS "Quality" mode
Secondly, it can increase the frame rate and resolution. The new AI network uses Tensor Cores more efficiently to achieve 2x the speed of the original version, which improves frame rates and removes previous limitations of graphics cards, settings and resolutions.
Currently, DLSS has been updated to version 2.4.0.
#Looking at the 2x improvement in game performance, frame rate and image quality are really nothing to say.
Now, NVIDIA DLSS has been used in 200 games and applications.
Netizens’ hot comments
After watching this video shown by NVIDIA, netizens are worried about their Will the graphics card explode?
What everyone is more concerned about is, when will Black Wukong come?
The above is the detailed content of 'Black Wukong' real-life demonstration explodes, NVIDIA shows off light tracing technology. For more information, please follow other related articles on the PHP Chinese website!
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
1670
14
1428
52
1329
25
1274
29
1256
24
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions
Jun 28, 2024 am 03:51 AM
This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP
Context-augmented AI coding assistant using Rag and Sem-Rag
Jun 10, 2024 am 11:08 AM
Improve developer productivity, efficiency, and accuracy by incorporating retrieval-enhanced generation and semantic memory into AI coding assistants. Translated from EnhancingAICodingAssistantswithContextUsingRAGandSEM-RAG, author JanakiramMSV. While basic AI programming assistants are naturally helpful, they often fail to provide the most relevant and correct code suggestions because they rely on a general understanding of the software language and the most common patterns of writing software. The code generated by these coding assistants is suitable for solving the problems they are responsible for solving, but often does not conform to the coding standards, conventions and styles of the individual teams. This often results in suggestions that need to be modified or refined in order for the code to be accepted into the application
Can fine-tuning really allow LLM to learn new things: introducing new knowledge may make the model produce more hallucinations
Jun 11, 2024 pm 03:57 PM
Large Language Models (LLMs) are trained on huge text databases, where they acquire large amounts of real-world knowledge. This knowledge is embedded into their parameters and can then be used when needed. The knowledge of these models is "reified" at the end of training. At the end of pre-training, the model actually stops learning. Align or fine-tune the model to learn how to leverage this knowledge and respond more naturally to user questions. But sometimes model knowledge is not enough, and although the model can access external content through RAG, it is considered beneficial to adapt the model to new domains through fine-tuning. This fine-tuning is performed using input from human annotators or other LLM creations, where the model encounters additional real-world knowledge and integrates it
Seven Cool GenAI & LLM Technical Interview Questions
Jun 07, 2024 am 10:06 AM
To learn more about AIGC, please visit: 51CTOAI.x Community https://www.51cto.com/aigc/Translator|Jingyan Reviewer|Chonglou is different from the traditional question bank that can be seen everywhere on the Internet. These questions It requires thinking outside the box. Large Language Models (LLMs) are increasingly important in the fields of data science, generative artificial intelligence (GenAI), and artificial intelligence. These complex algorithms enhance human skills and drive efficiency and innovation in many industries, becoming the key for companies to remain competitive. LLM has a wide range of applications. It can be used in fields such as natural language processing, text generation, speech recognition and recommendation systems. By learning from large amounts of data, LLM is able to generate text
Five schools of machine learning you don't know about
Jun 05, 2024 pm 08:51 PM
Machine learning is an important branch of artificial intelligence that gives computers the ability to learn from data and improve their capabilities without being explicitly programmed. Machine learning has a wide range of applications in various fields, from image recognition and natural language processing to recommendation systems and fraud detection, and it is changing the way we live. There are many different methods and theories in the field of machine learning, among which the five most influential methods are called the "Five Schools of Machine Learning". The five major schools are the symbolic school, the connectionist school, the evolutionary school, the Bayesian school and the analogy school. 1. Symbolism, also known as symbolism, emphasizes the use of symbols for logical reasoning and expression of knowledge. This school of thought believes that learning is a process of reverse deduction, through existing
To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework
Jul 25, 2024 am 06:42 AM
Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A
SOTA performance, Xiamen multi-modal protein-ligand affinity prediction AI method, combines molecular surface information for the first time
Jul 17, 2024 pm 06:37 PM
Editor | KX In the field of drug research and development, accurately and effectively predicting the binding affinity of proteins and ligands is crucial for drug screening and optimization. However, current studies do not take into account the important role of molecular surface information in protein-ligand interactions. Based on this, researchers from Xiamen University proposed a novel multi-modal feature extraction (MFE) framework, which for the first time combines information on protein surface, 3D structure and sequence, and uses a cross-attention mechanism to compare different modalities. feature alignment. Experimental results demonstrate that this method achieves state-of-the-art performance in predicting protein-ligand binding affinities. Furthermore, ablation studies demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within this framework. Related research begins with "S
SK Hynix will display new AI-related products on August 6: 12-layer HBM3E, 321-high NAND, etc.
Aug 01, 2024 pm 09:40 PM
According to news from this site on August 1, SK Hynix released a blog post today (August 1), announcing that it will attend the Global Semiconductor Memory Summit FMS2024 to be held in Santa Clara, California, USA from August 6 to 8, showcasing many new technologies. generation product. Introduction to the Future Memory and Storage Summit (FutureMemoryandStorage), formerly the Flash Memory Summit (FlashMemorySummit) mainly for NAND suppliers, in the context of increasing attention to artificial intelligence technology, this year was renamed the Future Memory and Storage Summit (FutureMemoryandStorage) to invite DRAM and storage vendors and many more players. New product SK hynix launched last year
