The laws of physics no longer apply as landscapes bend and flip, air and water blend together so that porpoises swim through the sky, surfers catch waves of clouds and the moon grows to many times its normal size. Jakarta-based graphic designer Jati Putra digitally blends photographs of nature, architecture and human subjects to create otherworldly scenes.

These creative compositions masterfully combine images that don’t really go together in the real world, but match up beautifully in mood, tone and color so the results are surreal, yet somehow almost believable. It makes it easy to imagine a world in which you can walk up to the edge of a cliff and see the moon floating in the clouds just off in the distance.

Other manipulations create Inception-like landscapes that fold upon themselves in strange ways, the shape of the Earth and gravity temporarily suspended. But some are so subtle it takes a moment to realize that the trees in a forest are mirrored, with roots and another soil surface where the leaves and sky should be.

Check out more of Putra’s work at his Instagram, @jatiputra.

Those of us working in creative fields have often consoled ourselves that although automation may claim many other jobs, at least robots can’t make art. That’s not exactly true for a variety of reasons (depending on how you define ‘art’), but it really goes out the window when you look at these astonishing images released recently by Google. The landscapes produced on the company’s image recognition neural network reveal the answer to the question, “Can artificial intelligence dream?”

It turns out that it can – sort of. Google created a method to ‘teach’ its neural network to identify features like animals, buildings and objects in photographs. The computer highlights the features it recognizes. When that modified image is fed back to the network again and again, it’s repeatedly altered until it produces bizarre mashups that belong in a gallery of surreal art.

Suddenly, an image of a knight on a horse is filled with ghostly impressions of frogs, fish, dogs and flowers. The knight’s arm seems to have sprouted a koala head, while the head of another unrecognizable animal emerges from beneath the horse’s tail. In another image, a tree and field turn cotton candy pink, and the clouds transform into conjoined sheep monsters.

Technically, it’s more like the computers were fed psychedelics and asked to paint, rather than capturing random images that might flash through their artificial ‘minds’ when they’re idle. The computers look for patterns and edges within the photos and paintings when they’re trying to identify objects and shapes, leading to those strange ghostly images scattered randomly throughout. Those edges are brought out more in each successive layer until the network starts thinking it sees all sorts of things within them.

Google describes it as “inceptionism,” saying “We know that after training, each  layer progressively extracts higher and higher-level features of the image, until the final layer essentially makes a decision on what the image shows.”

“So here’s one surprise: neural networks that were trained to discriminate between different kinds of images have quite a bit of the information needed to generate images too. Why is this important? Well, we train networks by simply showing them many examples of what we want them to learn, hoping they extract the essence of the matter at hand (e.g., a fork needs a handle and 2-4 tines), and learn to ignore what doesn’t matter (a fork can be any shape, size, color or orientation).”

“If we choose higher-level layers, which identify more sophisticated features in images, complex features or even whole objects tend to emerge. Again, we just start with an existing image and give it to our neural net. We ask the network: “Whatever you see there, I want more of it!” This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird. This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.”

Check out lots more examples on Google’s research blog.

What can’t artists do with 3D computer graphics these days? Fantasy can be brought to life in ways never before imagined, and realistic scenes as clear as a digital photograph are illustrated with stunning vitality. These 18 CG images from 15 talented artists will blow you away with their depth and attention to detail, from the tiniest little pores on the skin of an elf to the fibers on a fuzzy sweater.

Piotr Fox Wysocki

(image via: cgsociety.org)

The texture of the fabric. The gleam of the metal helmet. The pores, tiny hairs and imperfections of the skin. Piotr Fox Wysocki proves his mastery of 3D art with “The Last Elf”, a truly mind-blowing testament to how powerful 3D modeling programs have become. The project was certainly a labor of love, as Fox Wysocki notes that “As far as I
remember there were 1,300,000 small hair in the fabric.”

Juan Siquier

(image via: siquier.cgsociety.org)

3D artist Juan Siquier has managed to stir together a complex pot of magical ingredients to make this image so believable and moody: perspective, lighting, texture, and all of the little details that make up a personal space. See it full-sized on CGSociety.org to really appreciate the artistry of this image.

Arthur Wiechec

(image via: djdrako.deviantart.com)

Polish artist Arthur Wiechec may design everyday items like wine glasses and chess boards, but he infuses an incredible amount of life into them. Only the physical impossibility of floating wine and precariously balanced quarters of a glass betray the source of the image.

Kuanfu Sun

(image via: apollo13c.cgsociety.org)

Macro photo of a bee, or work of computer art? Kuanfu Sun makes it hard to tell in this image, which is richly detailed down to floating bits of dandelion in the background.

Rodrigue Pralier

(image via: 3dtotal.com)

Principal Artist at Bioware Montreal , Rodrigue Pralier has worked on 3D characters and backgrounds for games like Mass Effect 2 . This particular piece was done using Zbrush, 3Ds Max and Photoshop.

“I wanted to do a piece with an old Samurai. He just had a fight and won over another samurai. He is completely detached, he has done it so many times before. Now he just awaits for the one who will beat him, and end his nonsense life.”

Hong Phi

(image via: hongphi.deviantart.com)

If you saw one of Vietnamese conceptual 3D artist Hong Phi’s interiors in a magazine, you’d never guess that it wasn’t a photograph of a richly appointed home. But all of these images – including the incredible food spread above – were made using CG.

Rick Baker

(image via: monstermaker.cgsociety.org)

Renowned makeup artist Rick Baker turned to CGI to create a stunning likeness of Frankenstein’s monster. “This piece entitled “The Monster” is based on one of my favorite stills, of my all time favorite monster Boris Karloff as Frankenstein’s Monster,” he writes on CG Society.

“I used Modo ZBrush and Photoshop to create this piece. Jack Pierce had crude materials in 1931 to create this makeup but managed to create an image that the whole world knows. Besides trying to do a likeness of Karloff I hoped to show some of the emotion that he put into this character.”

Mauro Corveloni

(image via: maurocor.cgsociety.org)

Mauro Corveloni’s “Muriel” may not quite look like a real woman – there’s something sort of waxy about her – but what’s truly impressive here is both the lighting and all of those tiny, fuzzy fibers on her hat and sweater.

Finn Meinert Matthiesen

(image via: madmaximus83.deviantart.com)

It’s an idyllic scene – a romantic picnic with textured table linens, a glass wine bottle, fruit and a basket full of bread with a lilypad-covered lake in the background. German graphic designer Finn Meinert Matthiesen says he used 3D-Studio Max 2009, VRay and Photoshop to create this image.

Max Wahyudi

(image via: student.vfs.com)

It’s tempting to assume that Max Wahyudi must have just edited an image of Heath Ledger as The Joker for this image – such is its realism. But you can see the whole fascinating modeling process laid out step-by-step at Max’s website, as each element is carefully arranged and enhanced.

Max Kor

(image via: mkor.cgsociety.org)

Each tiny eyelash, fine little hair, bump, wrinkle and scar make this 3D CG image by Max Kor astonishingly realistic – not to mention the reflections on the figure’s chain mail. And this image isn’t even an example of the latest and greatest 3D technology – it was created in 2005, making it all the more impressive.

Ed Whetstone

(image via: edthehobbit.cgsociety.org)

“This project was all about texturing something deceptively simple, the Sultan of Slime, the humble snail,” artist Ed Whetstone explains. “Then, the challenge was to composite it convincingly onto a photographic plate. The trickiest bit was replicating the very particular pattern of bumps and protrusions that snails always exhibit. This particular snail isn’t based on any specific species, but a mishmash of ones I thought looked interesting.”

Pasquale Giacobelli

(image via: karma3d.cgsociety.org)

Pasquale Giacobelli’s images may not have quite the crispness and shocking realism as some of his fellow 3D artists, but his art has a special something that many of them are lacking – humanity. There’s something in the eyes of his subjects that seems more fully alive than most computer-generated portraits.

Cornelius Comanns

(image via: cernulois.cgsociety.org)

Reflections can be tough to get right in any artistic work, but Cornelius Comanns has certainly crafted them convincingly in this piece, featuring an ice cube and two ladybugs.

Alex Stratulat

(image via: alexstratulat.cgsociety.org)

It really takes a moment to realize you’re not looking at an actual photograph of a young woman in this 3D work of art by Alex Stratulat.

If you think that digital art has no soul or dimension, you haven’t seen the work of these 15 visionary visual artists. Some work as concept artists or illustrators while others take more of a fine art approach, creating purely for their own pleasure. Many of them have backgrounds in traditional art, seeing the use of digital media such as Photoshop and Corel Painter as a natural evolution of the creative process but never losing sight of those mysterious elements that make a work of art truly effective.

Ray Caesar

Ray Caesar’s 17 years working in the Art and Photography Department of the Hospital for Sick Children in Toronto has had a lasting impression on his work. One of the most famous and sought-after digital artists of the Pop Surrealism movement, Caesar has a unique style that blends otherworldly images with Victorian aesthetics. He creates models in a 3D modeling software called Maya, then wraps them in painted and manipulated texture maps and adds digital lights and shadows.

Bobby Chui

Digital painter Bobby Chui got his start designing Disney, Warner Bros. and Star Wars toys and that playful, imaginative tone remains in his illustration work for film and television today. Chui teaches digital painting at Schoolism.com and has won a number of CG Choice Awards from the CG Society of Digital Artists.

Of his choice to work with digital rather than traditional materials, Chui told It’s Art Magazine, “When I experimented a bit with Illustrator and Photoshop 3 I quickly realized that ‘digital’ will be the way to go in the near future. With digital art there is no need to buy paint or canvases and you can take your art with you to work on almost anywhere. You can’t do that using traditional materials.”

Cristiano Siqueira

Cristiano Siqueira, known as CrisVector, is a digital artist from Brazil who uses vectors, Photoshop and 3D to create his unique artwork. A former graphic designer, Siqueira was itching for a bit more creative freedom, which he has found now as a self-employed illustrator.

Siqueira told Abduzeedo, “All my illustrations are done entirely digitally I usually use 3 basic techniques: digital composition, digital painting and vectorial illustration. These techniques blend with each other many times, I may use composition elements on a painting (pictures insertion, for exemple), using vectorial elements in a composition or using digital painting elements in a vector illustration.”

Daniel Conway

UK artist Daniel Conway started out as an animator, but became intrigued by digital painting and soon taught himself how to create stunningly detailed fantasy art with a combination of Photoshop and Painter with a Wacom Cintiq, the hybrid LCD display and graphics tablet.

“I have a fascination with finding beauty amongst chaos,” Conway told ImagineFX. “I’ve always found the most memorable pieces of art are those that had some kind of an emotional impact on me. I really enjoy creating something that people can engage with. Emotion can be conveyed visually in many ways, from lighting and colour to the poses and facial expressions of characters.”

Sarah Rose Oliver

UK art student Sarah Rose Oliver hasn’t even graduated yet and she’s already making waves in the world of digital art, creating eye-catching pieces that have landed her on many a list of amazing digital painters. Her photo-realistic style is especially effective in portraits, which she creates using a Genius Pen Tablet and Photoshop.

Alberto Seveso

He might have no formal training in art, but Alberto Seveso clearly doesn’t need it. He has pioneered his own technique, which he named ‘sperm shaping’ for the shape of the vectors that he combines with images to create his own unique style. Many have asked Seveso to provide a tutorial but he refuses as he doesn’t want “clones of Alberto Seveso” running around and instead encourages other artists to go in their own direction.

Marek Okon

Polish artist Marek Okon creates each of his digital paintings as if they were a scene in a movie, capturing the most climactic moment of the story. A professional painter and concept designer, Okon produces his epic work on a Wacom Intuos3 A4 tablet.

On where he gets his inspiration, Okon told Psd tuts+, “When its a book cover, inspiration comes from the story I’m reading. During reading I see all the scenes in my imagination and then I pick one that will fit the cover best, one that will draw attention of the people passing by this book. When its personal works I usually create my own little story around the picture, so every piece of equipment presented, every location and character has its part in the world presented. I rarely go and create something accidental.”

Cris de Lara

Cristina de Lara Stockler, known professionally as Cris de Lara, made a name for herself in the world of digital art through her unique old-style pin-ups. Much of her work has a comic book feel due to the influence that working in the industry had upon her style.

De Lara told It’s Art Magazine, “The most important thing is what you can produce with your talent and skills, of course, the right tools help a lot, but you need to improve your skills every day to be independent of the digital weapons. If you really want to be an artist, in a digital environment, for sure a painting program helps a lot, but you should study art, painting, drawing, the masters and their styles and techniques, and so on, instead of being the best Photoshop operator, for instance.”

Tae young Choi

Game concept designer Tae young Choi uses Painter, Photoshop, 3ds Max and Maya to create imagery that fuses dystopian sci-fi and classical mysticism for his current employer, console game developer Midway. Though he says he’d like to work with more traditional media, he explained to Imagine FX that time and practical issues get in the way.

“As a professional concept artist, I need to create art very quickly and I’m asked to change the painting very often. That’s one of the main reasons for choosing digital techniques rather than traditional material at work. I guess I can be a ‘real’ painter after my retirement…”

Craig Sellars

Freelance visual development artist and concept artist Craig Sellars has a background in both classical animation and video games, and it shows in his work, which has a traditional painterly quality but illustrates the sort of bleak interiors and desolate landscapes that are commonly seen in games.

Wen Xi-Chen

UK/Shanghai-based artist Wen Xi-Chen is a pathology student by day, digital painter by night, creating stunning portraits using Wacom Tablet (Intuos2) in Photoshop and/or Painter Classic/ Painter X. She offers a number of tutorials on deviantART.

Don Seegmiller

Don Seegmiller is an artist, author and educator, passing on his gift for digital art at Brigham Young University. He has completed more than 600 paintings in 20 years, has had his work featured in a number of books and is a regular speaker at the Game Developers Conference.

A Corel Painter Master, Seegmiller says “A great deal of work in the video game, movie and other entertainment industries requires the development of a relatively rough concept sketch of a character into a more finished and refined piece of art. Often, this is not only to sell the concept, but also to give other people who will be working on the various aspects of the project a clear idea of the artist’s vision.”

Alon Chou

Taiwanese freelance digital artist Alon Chou worked in traditional media like oil painting and watercolor while a student at National Taiwan University of Art, and began learning digital art media only after taking a 3D modeling job with XPEC. Though he excelled at CG, Chou still identifies more with traditional artists in terms of his subject matter and style.

Chou told It’s Art Magazine, “What I want to express in my art is similar to the dramatic appeals in traditional drawings. I always hope to have a complete composition and plot.  As for the contents of paintings, I wish to start with the emotions of daily life because we humans have all sorts of feelings. Anything picked up from daily life has the chance of becoming a touching piece of art work.  Therefore, if there’s people involved in the work, I will make the emotion I want to express as the starting point.”

Marta Dahlig

One of the most popular artists on deviantART, Poland-based Marta Dahlig has gained a reputation for beautiful digital fantasy art. Dahlig uses modern tools like Photoshop and Corel Painter to create her works, but is inspired by classicists like William Bouguereau. Best known for her ‘Seven Deadly Sins’ series, Dahlig provides tutorials on YouTube and various websites so that others can see exactly how she produces her art.

Linda Bergkvist

Swedish illustrator and digital fantasy artist Linda Bergkvist, known online as Enayla, started out as a traditional painter. When she was given a Wacom tablet on her 20th birthday by her parents, Bergkvist didn’t even think she would use it. But soon enough, she was hooked, and since then she has become one of the most talked-about CG artists and worked as a conceptual artist on the film The Golden Compass.